Search | arXiv e-print repository

<!DOCTYPE html> <html lang="en"> <head> <meta charset="utf-8"/> <meta name="viewport" content="width=device-width, initial-scale=1"/>  <link rel="apple-touch-icon" sizes="180x180" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/apple-touch-icon.png"> <link rel="icon" type="image/png" sizes="32x32" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-32x32.png"> <link rel="icon" type="image/png" sizes="16x16" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-16x16.png"> <link rel="manifest" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/site.webmanifest"> <link rel="mask-icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/safari-pinned-tab.svg" color="#b31b1b"> <link rel="shortcut icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon.ico"> <meta name="msapplication-TileColor" content="#b31b1b"> <meta name="msapplication-config" content="images/icons/browserconfig.xml"> <meta name="theme-color" content="#b31b1b">  <title>Search | arXiv e-print repository</title> <script defer src="https://static.arxiv.org/static/base/1.0.0a5/fontawesome-free-5.11.2-web/js/all.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/base/1.0.0a5/css/arxivstyle.css" /> <script type="text/x-mathjax-config"> MathJax.Hub.Config({ messageStyle: "none", extensions: ["tex2jax.js"], jax: ["input/TeX", "output/HTML-CSS"], tex2jax: { inlineMath: [ ['$','$'], ["\$","\$"] ], displayMath: [ ['$$','$$'], ["\\[","\\]"] ], processEscapes: true, ignoreClass: '.*', processClass: 'mathjax.*' }, TeX: { extensions: ["AMSmath.js", "AMSsymbols.js", "noErrors.js"], noErrors: { inlineDelimiters: ["$","$"], multiLine: false, style: { "font-size": "normal", "border": "" } } }, "HTML-CSS": { availableFonts: ["TeX"] } }); </script> <script src='//static.arxiv.org/MathJax-2.7.3/MathJax.js'></script> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/notification.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/bulma-tooltip.min.css" /> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/search.css" /> <script src="https://code.jquery.com/jquery-3.2.1.slim.min.js" integrity="sha256-k2WSCIexGzOj3Euiig+TlR8gA0EmPjuc79OEeY5L45g=" crossorigin="anonymous"></script> <script src="https://static.arxiv.org/static/search/0.5.6/js/fieldset.js"></script> <style> radio#cf-customfield_11400 { display: none; } </style> </head> <body> <header><a href="#main-container" class="is-sr-only">Skip to main content</a>  <div class="attribution level is-marginless" role="banner"> <div class="level-left"> <a class="level-item" href="https://cornell.edu/"><img src="https://static.arxiv.org/static/base/1.0.0a5/images/cornell-reduced-white-SMALL.svg" alt="Cornell University" width="200" aria-label="logo" /></a> </div> <div class="level-right is-marginless"><p class="sponsors level-item is-marginless"><span id="support-ack-url">We gratefully acknowledge support from<br /> the Simons Foundation, <a href="https://info.arxiv.org/about/ourmembers.html">member institutions</a>, and all contributors. <a href="https://info.arxiv.org/about/donate.html">Donate</a></span></p></div> </div>  <div class="identity level is-marginless"> <div class="level-left"> <div class="level-item"> <a class="arxiv" href="https://arxiv.org/" aria-label="arxiv-logo"> <img src="https://static.arxiv.org/static/base/1.0.0a5/images/arxiv-logo-one-color-white.svg" aria-label="logo" alt="arxiv logo" width="85" style="width:85px;"/> </a> </div> </div> <div class="search-block level-right"> <form class="level-item mini-search" method="GET" action="https://arxiv.org/search"> <div class="field has-addons"> <div class="control"> <input class="input is-small" type="text" name="query" placeholder="Search..." aria-label="Search term or terms" /> <p class="help"><a href="https://info.arxiv.org/help">Help</a> | <a href="https://arxiv.org/search/advanced">Advanced Search</a></p> </div> <div class="control"> <div class="select is-small"> <select name="searchtype" aria-label="Field to search"> <option value="all" selected="selected">All fields</option> <option value="title">Title</option> <option value="author">Author</option> <option value="abstract">Abstract</option> <option value="comments">Comments</option> <option value="journal_ref">Journal reference</option> <option value="acm_class">ACM classification</option> <option value="msc_class">MSC classification</option> <option value="report_num">Report number</option> <option value="paper_id">arXiv identifier</option> <option value="doi">DOI</option> <option value="orcid">ORCID</option> <option value="author_id">arXiv author ID</option> <option value="help">Help pages</option> <option value="full_text">Full text</option> </select> </div> </div> <input type="hidden" name="source" value="header"> <button class="button is-small is-cul-darker">Search</button> </div> </form> </div> </div>  <div class="container"> <div class="user-tools is-size-7 has-text-right has-text-weight-bold" role="navigation" aria-label="User menu"> <a href="https://arxiv.org/login">Login</a> </div> </div> </header> <main class="container" id="main-container"> <div class="level is-marginless"> <div class="level-left"> <h1 class="title is-clearfix"> Showing 1–50 of 150 results for author: <span class="mathjax">Hong, C S</span> </h1> </div> <div class="level-right is-hidden-mobile">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> <div class="content"> <form method="GET" action="/search/cs" aria-role="search"> Searching in archive <strong>cs</strong>. <a href="/search/?searchtype=author&query=Hong%2C+C+S">Search in all archives.</a> <div class="field has-addons-tablet"> <div class="control is-expanded"> <label for="query" class="hidden-label">Search term or terms</label> <input class="input is-medium" id="query" name="query" placeholder="Search term..." type="text" value="Hong, C S"> </div> <div class="select control is-medium"> <label class="is-hidden" for="searchtype">Field</label> <select class="is-medium" id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> </div> <div class="control"> <button class="button is-link is-medium">Search</button> </div> </div> <div class="field"> <div class="control is-size-7"> <label class="radio"> <input checked id="abstracts-0" name="abstracts" type="radio" value="show"> Show abstracts </label> <label class="radio"> <input id="abstracts-1" name="abstracts" type="radio" value="hide"> Hide abstracts </label> </div> </div> <div class="is-clearfix" style="height: 2.5em"> <div class="is-pulled-right"> <a href="/search/advanced?terms-0-term=Hong%2C+C+S&terms-0-field=author&size=50&order=-announced_date_first">Advanced Search</a> </div> </div> <input type="hidden" name="order" value="-announced_date_first"> <input type="hidden" name="size" value="50"> </form> <div class="level breathe-horizontal"> <div class="level-left"> <form method="GET" action="/search/"> <div style="display: none;"> <select id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> <input id="query" name="query" type="text" value="Hong, C S"> <ul id="abstracts"><li><input checked id="abstracts-0" name="abstracts" type="radio" value="show"> <label for="abstracts-0">Show abstracts</label></li><li><input id="abstracts-1" name="abstracts" type="radio" value="hide"> <label for="abstracts-1">Hide abstracts</label></li></ul> </div> <div class="box field is-grouped is-grouped-multiline level-item"> <div class="control"> <span class="select is-small"> <select id="size" name="size"><option value="25">25</option><option selected value="50">50</option><option value="100">100</option><option value="200">200</option></select> </span> <label for="size">results per page</label>. </div> <div class="control"> <label for="order">Sort results by</label> <span class="select is-small"> <select id="order" name="order"><option selected value="-announced_date_first">Announcement date (newest first)</option><option value="announced_date_first">Announcement date (oldest first)</option><option value="-submitted_date">Submission date (newest first)</option><option value="submitted_date">Submission date (oldest first)</option><option value="">Relevance</option></select> </span> </div> <div class="control"> <button class="button is-small is-link">Go</button> </div> </div> </form> </div> </div> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Hong%2C+C+S&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Hong%2C+C+S&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Hong%2C+C+S&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Hong%2C+C+S&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Hong%2C+C+S&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> </ul> </nav> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.15257">arXiv:2501.15257</a> <span> [<a href="https://arxiv.org/pdf/2501.15257">pdf</a>, <a href="https://arxiv.org/format/2501.15257">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Pre-trained Model Guided Mixture Knowledge Distillation for Adversarial Federated Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Qiao%2C+Y">Yu Qiao</a>, <a href="/search/cs?searchtype=author&query=Le%2C+H+Q">Huy Q. Le</a>, <a href="/search/cs?searchtype=author&query=Adhikary%2C+A">Apurba Adhikary</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.15257v1-abstract-short" style="display: inline;"> This paper aims to improve the robustness of a small global model while maintaining clean accuracy under adversarial attacks and non-IID challenges in federated learning. By leveraging the concise knowledge embedded in the class probabilities from a pre-trained model for both clean and adversarial image classification, we propose a Pre-trained Model-guided Adversarial Federated Learning (PM-AFL) t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.15257v1-abstract-full').style.display = 'inline'; document.getElementById('2501.15257v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.15257v1-abstract-full" style="display: none;"> This paper aims to improve the robustness of a small global model while maintaining clean accuracy under adversarial attacks and non-IID challenges in federated learning. By leveraging the concise knowledge embedded in the class probabilities from a pre-trained model for both clean and adversarial image classification, we propose a Pre-trained Model-guided Adversarial Federated Learning (PM-AFL) training paradigm. This paradigm integrates vanilla mixture and adversarial mixture knowledge distillation to effectively balance accuracy and robustness while promoting local models to learn from diverse data. Specifically, for clean accuracy, we adopt a dual distillation strategy where the class probabilities of randomly paired images and their blended versions are aligned between the teacher model and the local models. For adversarial robustness, we use a similar distillation approach but replace clean samples on the local side with adversarial examples. Moreover, considering the bias between local and global models, we also incorporate a consistency regularization term to ensure that local adversarial predictions stay aligned with their corresponding global clean ones. These strategies collectively enable local models to absorb diverse knowledge from the teacher model while maintaining close alignment with the global model, thereby mitigating overfitting to local optima and enhancing the generalization of the global model. Experiments demonstrate that the PM-AFL-based paradigm outperforms other methods that integrate defense strategies by a notable margin. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.15257v1-abstract-full').style.display = 'none'; document.getElementById('2501.15257v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.08521">arXiv:2501.08521</a> <span> [<a href="https://arxiv.org/pdf/2501.08521">pdf</a>, <a href="https://arxiv.org/format/2501.08521">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Mitigating Domain Shift in Federated Learning via Intra- and Inter-Domain Prototypes </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Le%2C+H+Q">Huy Q. Le</a>, <a href="/search/cs?searchtype=author&query=Tun%2C+Y+L">Ye Lin Tun</a>, <a href="/search/cs?searchtype=author&query=Qiao%2C+Y">Yu Qiao</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+M+N+H">Minh N. H. Nguyen</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+K+O">Keon Oh Kim</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.08521v1-abstract-short" style="display: inline;"> Federated Learning (FL) has emerged as a decentralized machine learning technique, allowing clients to train a global model collaboratively without sharing private data. However, most FL studies ignore the crucial challenge of heterogeneous domains where each client has a distinct feature distribution, which is common in real-world scenarios. Prototype learning, which leverages the mean feature ve… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.08521v1-abstract-full').style.display = 'inline'; document.getElementById('2501.08521v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.08521v1-abstract-full" style="display: none;"> Federated Learning (FL) has emerged as a decentralized machine learning technique, allowing clients to train a global model collaboratively without sharing private data. However, most FL studies ignore the crucial challenge of heterogeneous domains where each client has a distinct feature distribution, which is common in real-world scenarios. Prototype learning, which leverages the mean feature vectors within the same classes, has become a prominent solution for federated learning under domain skew. However, existing federated prototype learning methods only consider inter-domain prototypes on the server and overlook intra-domain characteristics. In this work, we introduce a novel federated prototype learning method, namely I$^2$PFL, which incorporates $\textbf{I}$ntra-domain and $\textbf{I}$nter-domain $\textbf{P}$rototypes, to mitigate domain shifts and learn a generalized global model across multiple domains in federated learning. To construct intra-domain prototypes, we propose feature alignment with MixUp-based augmented prototypes to capture the diversity of local domains and enhance the generalization of local features. Additionally, we introduce a reweighting mechanism for inter-domain prototypes to generate generalized prototypes to provide inter-domain knowledge and reduce domain skew across multiple clients. Extensive experiments on the Digits, Office-10, and PACS datasets illustrate the superior performance of our method compared to other baselines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.08521v1-abstract-full').style.display = 'none'; document.getElementById('2501.08521v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">13 pages, 9 figures, 10 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.19354">arXiv:2412.19354</a> <span> [<a href="https://arxiv.org/pdf/2412.19354">pdf</a>, <a href="https://arxiv.org/format/2412.19354">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Qiao%2C+Y">Yu Qiao</a>, <a href="/search/cs?searchtype=author&query=Adhikary%2C+A">Apurba Adhikary</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+K">Kitae Kim</a>, <a href="/search/cs?searchtype=author&query=Huh%2C+E">Eui-Nam Huh</a>, <a href="/search/cs?searchtype=author&query=Han%2C+Z">Zhu Han</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.19354v1-abstract-short" style="display: inline;"> Federated learning (FL) is a distributed training technology that enhances data privacy in mobile edge networks by allowing data owners to collaborate without transmitting raw data to the edge server. However, data heterogeneity and adversarial attacks pose challenges to develop an unbiased and robust global model for edge deployment. To address this, we propose Federated hyBrid Adversarial traini… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.19354v1-abstract-full').style.display = 'inline'; document.getElementById('2412.19354v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.19354v1-abstract-full" style="display: none;"> Federated learning (FL) is a distributed training technology that enhances data privacy in mobile edge networks by allowing data owners to collaborate without transmitting raw data to the edge server. However, data heterogeneity and adversarial attacks pose challenges to develop an unbiased and robust global model for edge deployment. To address this, we propose Federated hyBrid Adversarial training and self-adversarial disTillation (FedBAT), a new framework designed to improve both robustness and generalization of the global model. FedBAT seamlessly integrates hybrid adversarial training and self-adversarial distillation into the conventional FL framework from data augmentation and feature distillation perspectives. From a data augmentation perspective, we propose hybrid adversarial training to defend against adversarial attacks by balancing accuracy and robustness through a weighted combination of standard and adversarial training. From a feature distillation perspective, we introduce a novel augmentation-invariant adversarial distillation method that aligns local adversarial features of augmented images with their corresponding unbiased global clean features. This alignment can effectively mitigate bias from data heterogeneity while enhancing both the robustness and generalization of the global model. Extensive experimental results across multiple datasets demonstrate that FedBAT yields comparable or superior performance gains in improving robustness while maintaining accuracy compared to several baselines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.19354v1-abstract-full').style.display = 'none'; document.getElementById('2412.19354v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.17241">arXiv:2412.17241</a> <span> [<a href="https://arxiv.org/pdf/2412.17241">pdf</a>, <a href="https://arxiv.org/format/2412.17241">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> QTSeg: A Query Token-Based Dual-Mix Attention Framework with Multi-Level Feature Distribution for Medical Image Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tran%2C+P">Phuong-Nam Tran</a>, <a href="/search/cs?searchtype=author&query=Pham%2C+N+T">Nhat Truong Pham</a>, <a href="/search/cs?searchtype=author&query=Dang%2C+D+N+M">Duc Ngoc Minh Dang</a>, <a href="/search/cs?searchtype=author&query=Huh%2C+E">Eui-Nam Huh</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.17241v2-abstract-short" style="display: inline;"> Medical image segmentation plays a crucial role in assisting healthcare professionals with accurate diagnoses and enabling automated diagnostic processes. Traditional convolutional neural networks (CNNs) often struggle with capturing long-range dependencies, while transformer-based architectures, despite their effectiveness, come with increased computational complexity. Recent efforts have focused… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.17241v2-abstract-full').style.display = 'inline'; document.getElementById('2412.17241v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.17241v2-abstract-full" style="display: none;"> Medical image segmentation plays a crucial role in assisting healthcare professionals with accurate diagnoses and enabling automated diagnostic processes. Traditional convolutional neural networks (CNNs) often struggle with capturing long-range dependencies, while transformer-based architectures, despite their effectiveness, come with increased computational complexity. Recent efforts have focused on combining CNNs and transformers to balance performance and efficiency, but existing approaches still face challenges in achieving high segmentation accuracy while maintaining low computational costs. Furthermore, many methods underutilize the CNN encoder's capability to capture local spatial information, concentrating primarily on mitigating long-range dependency issues. To address these limitations, we propose QTSeg, a novel architecture for medical image segmentation that effectively integrates local and global information. QTSeg features a dual-mix attention decoder designed to enhance segmentation performance through: (1) a cross-attention mechanism for improved feature alignment, (2) a spatial attention module to capture long-range dependencies, and (3) a channel attention block to learn inter-channel relationships. Additionally, we introduce a multi-level feature distribution module, which adaptively balances feature propagation between the encoder and decoder, further boosting performance. Extensive experiments on five publicly available datasets covering diverse segmentation tasks, including lesion, polyp, breast cancer, cell, and retinal vessel segmentation, demonstrate that QTSeg outperforms state-of-the-art methods across multiple evaluation metrics while maintaining lower computational costs. Our implementation can be found at: https://github.com/tpnam0901/QTSeg (v1.0.0) <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.17241v2-abstract-full').style.display = 'none'; document.getElementById('2412.17241v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.03871">arXiv:2412.03871</a> <span> [<a href="https://arxiv.org/pdf/2412.03871">pdf</a>, <a href="https://arxiv.org/format/2412.03871">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> CLIP-PING: Boosting Lightweight Vision-Language Models with Proximus Intrinsic Neighbors Guidance </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Thwal%2C+C+M">Chu Myaet Thwal</a>, <a href="/search/cs?searchtype=author&query=Tun%2C+Y+L">Ye Lin Tun</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+M+N+H">Minh N. H. Nguyen</a>, <a href="/search/cs?searchtype=author&query=Huh%2C+E">Eui-Nam Huh</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.03871v1-abstract-short" style="display: inline;"> Beyond the success of Contrastive Language-Image Pre-training (CLIP), recent trends mark a shift toward exploring the applicability of lightweight vision-language models for resource-constrained scenarios. These models often deliver suboptimal performance when relying solely on a single image-text contrastive learning objective, spotlighting the need for more effective training mechanisms that gua… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.03871v1-abstract-full').style.display = 'inline'; document.getElementById('2412.03871v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.03871v1-abstract-full" style="display: none;"> Beyond the success of Contrastive Language-Image Pre-training (CLIP), recent trends mark a shift toward exploring the applicability of lightweight vision-language models for resource-constrained scenarios. These models often deliver suboptimal performance when relying solely on a single image-text contrastive learning objective, spotlighting the need for more effective training mechanisms that guarantee robust cross-modal feature alignment. In this work, we propose CLIP-PING: Contrastive Language-Image Pre-training with Proximus Intrinsic Neighbors Guidance, a simple and efficient training paradigm designed to boost the performance of lightweight vision-language models with minimal computational overhead and lower data demands. CLIP-PING bootstraps unimodal features extracted from arbitrary pre-trained encoders to obtain intrinsic guidance of proximus neighbor samples, i.e., nearest-neighbor (NN) and cross nearest-neighbor (XNN). We find that extra contrastive supervision from these neighbors substantially boosts cross-modal alignment, enabling lightweight models to learn more generic features with rich semantic diversity. Extensive experiments reveal that CLIP-PING notably surpasses its peers in zero-shot generalization and cross-modal retrieval tasks. Specifically, a 5.5% gain on zero-shot ImageNet1K with 10.7% (I2T) and 5.7% (T2I) on Flickr30K, compared to the original CLIP when using ViT-XS image encoder trained on 3 million (image, text) pairs. Moreover, CLIP-PING showcases strong transferability under the linear evaluation protocol across several downstream tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.03871v1-abstract-full').style.display = 'none'; document.getElementById('2412.03871v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">15 pages, 4 figures, 20 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.13602">arXiv:2410.13602</a> <span> [<a href="https://arxiv.org/pdf/2410.13602">pdf</a>, <a href="https://arxiv.org/format/2410.13602">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Towards Satellite Non-IID Imagery: A Spectral Clustering-Assisted Federated Learning Approach </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zou%2C+L">Luyao Zou</a>, <a href="/search/cs?searchtype=author&query=Park%2C+Y+M">Yu Min Park</a>, <a href="/search/cs?searchtype=author&query=Thwal%2C+C+M">Chu Myaet Thwal</a>, <a href="/search/cs?searchtype=author&query=Tun%2C+Y+K">Yan Kyaw Tun</a>, <a href="/search/cs?searchtype=author&query=Han%2C+Z">Zhu Han</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.13602v2-abstract-short" style="display: inline;"> Low Earth orbit (LEO) satellites are capable of gathering abundant Earth observation data (EOD) to enable different Internet of Things (IoT) applications. However, to accomplish an effective EOD processing mechanism, it is imperative to investigate: 1) the challenge of processing the observed data without transmitting those large-size data to the ground because the connection between the satellite… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13602v2-abstract-full').style.display = 'inline'; document.getElementById('2410.13602v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.13602v2-abstract-full" style="display: none;"> Low Earth orbit (LEO) satellites are capable of gathering abundant Earth observation data (EOD) to enable different Internet of Things (IoT) applications. However, to accomplish an effective EOD processing mechanism, it is imperative to investigate: 1) the challenge of processing the observed data without transmitting those large-size data to the ground because the connection between the satellites and the ground stations is intermittent, and 2) the challenge of processing the non-independent and identically distributed (non-IID) satellite data. In this paper, to cope with those challenges, we propose an orbit-based spectral clustering-assisted clustered federated self-knowledge distillation (OSC-FSKD) approach for each orbit of an LEO satellite constellation, which retains the advantage of FL that the observed data does not need to be sent to the ground. Specifically, we introduce normalized Laplacian-based spectral clustering (NLSC) into federated learning (FL) to create clustered FL in each round to address the challenge resulting from non-IID data. Particularly, NLSC is adopted to dynamically group clients into several clusters based on cosine similarities calculated by model updates. In addition, self-knowledge distillation is utilized to construct each local client, where the most recent updated local model is used to guide current local model training. Experiments demonstrate that the observation accuracy obtained by the proposed method is separately 1.01x, 2.15x, 1.10x, and 1.03x higher than that of pFedSD, FedProx, FedAU, and FedALA approaches using the SAT4 dataset. The proposed method also shows superiority when using other datasets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13602v2-abstract-full').style.display = 'none'; document.getElementById('2410.13602v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 17 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10 pages, 5 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.13260">arXiv:2410.13260</a> <span> [<a href="https://arxiv.org/pdf/2410.13260">pdf</a>, <a href="https://arxiv.org/format/2410.13260">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/TNSM.2024.3517621">10.1109/TNSM.2024.3517621 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Cyber Attacks Prevention Towards Prosumer-based EV Charging Stations: An Edge-assisted Federated Prototype Knowledge Distillation Approach </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zou%2C+L">Luyao Zou</a>, <a href="/search/cs?searchtype=author&query=Vo%2C+Q+H">Quang Hieu Vo</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+K">Kitae Kim</a>, <a href="/search/cs?searchtype=author&query=Le%2C+H+Q">Huy Q. Le</a>, <a href="/search/cs?searchtype=author&query=Thwal%2C+C+M">Chu Myaet Thwal</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chaoning Zhang</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.13260v3-abstract-short" style="display: inline;"> In this paper, cyber-attack prevention for the prosumer-based electric vehicle (EV) charging stations (EVCSs) is investigated, which covers two aspects: 1) cyber-attack detection on prosumers' network traffic (NT) data, and 2) cyber-attack intervention. To establish an effective prevention mechanism, several challenges need to be tackled, for instance, the NT data per prosumer may be non-independe… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13260v3-abstract-full').style.display = 'inline'; document.getElementById('2410.13260v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.13260v3-abstract-full" style="display: none;"> In this paper, cyber-attack prevention for the prosumer-based electric vehicle (EV) charging stations (EVCSs) is investigated, which covers two aspects: 1) cyber-attack detection on prosumers' network traffic (NT) data, and 2) cyber-attack intervention. To establish an effective prevention mechanism, several challenges need to be tackled, for instance, the NT data per prosumer may be non-independent and identically distributed (non-IID), and the boundary between benign and malicious traffic becomes blurred. To this end, we propose an edge-assisted federated prototype knowledge distillation (E-FPKD) approach, where each client is deployed on a dedicated local edge server (DLES) and can report its availability for joining the federated learning (FL) process. Prior to the E-FPKD approach, to enhance accuracy, the Pearson Correlation Coefficient is adopted for feature selection. Regarding the proposed E-FPKD approach, we integrate the knowledge distillation and prototype aggregation technique into FL to deal with the non-IID challenge. To address the boundary issue, instead of directly calculating the distance between benign and malicious traffic, we consider maximizing the overall detection correctness of all prosumers (ODC), which can mitigate the computational cost compared with the former way. After detection, a rule-based method will be triggered at each DLES for cyber-attack intervention. Experimental analysis demonstrates that the proposed E-FPKD can achieve the largest ODC on NSL-KDD, UNSW-NB15, and IoTID20 datasets in both binary and multi-class classification, compared with baselines. For instance, the ODC for IoTID20 obtained via the proposed method is separately 0.3782% and 4.4471% greater than FedProto and FedAU in multi-class classification. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13260v3-abstract-full').style.display = 'none'; document.getElementById('2410.13260v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 17 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by IEEE Transactions on Network and Service Management</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.18718">arXiv:2409.18718</a> <span> [<a href="https://arxiv.org/pdf/2409.18718">pdf</a>, <a href="https://arxiv.org/format/2409.18718">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Enhancing Spectrum Efficiency in 6G Satellite Networks: A GAIL-Powered Policy Learning via Asynchronous Federated Inverse Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hassan%2C+S+S">Sheikh Salman Hassan</a>, <a href="/search/cs?searchtype=author&query=Park%2C+Y+M">Yu Min Park</a>, <a href="/search/cs?searchtype=author&query=Tun%2C+Y+K">Yan Kyaw Tun</a>, <a href="/search/cs?searchtype=author&query=Saad%2C+W">Walid Saad</a>, <a href="/search/cs?searchtype=author&query=Han%2C+Z">Zhu Han</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.18718v1-abstract-short" style="display: inline;"> In this paper, a novel generative adversarial imitation learning (GAIL)-powered policy learning approach is proposed for optimizing beamforming, spectrum allocation, and remote user equipment (RUE) association in NTNs. Traditional reinforcement learning (RL) methods for wireless network optimization often rely on manually designed reward functions, which can require extensive parameter tuning. To… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.18718v1-abstract-full').style.display = 'inline'; document.getElementById('2409.18718v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.18718v1-abstract-full" style="display: none;"> In this paper, a novel generative adversarial imitation learning (GAIL)-powered policy learning approach is proposed for optimizing beamforming, spectrum allocation, and remote user equipment (RUE) association in NTNs. Traditional reinforcement learning (RL) methods for wireless network optimization often rely on manually designed reward functions, which can require extensive parameter tuning. To overcome these limitations, we employ inverse RL (IRL), specifically leveraging the GAIL framework, to automatically learn reward functions without manual design. We augment this framework with an asynchronous federated learning approach, enabling decentralized multi-satellite systems to collaboratively derive optimal policies. The proposed method aims to maximize spectrum efficiency (SE) while meeting minimum information rate requirements for RUEs. To address the non-convex, NP-hard nature of this problem, we combine the many-to-one matching theory with a multi-agent asynchronous federated IRL (MA-AFIRL) framework. This allows agents to learn through asynchronous environmental interactions, improving training efficiency and scalability. The expert policy is generated using the Whale optimization algorithm (WOA), providing data to train the automatic reward function within GAIL. Simulation results show that the proposed MA-AFIRL method outperforms traditional RL approaches, achieving a $14.6\%$ improvement in convergence and reward value. The novel GAIL-driven policy learning establishes a novel benchmark for 6G NTN optimization. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.18718v1-abstract-full').style.display = 'none'; document.getElementById('2409.18718v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Submitted to IEEE Transactions on Mobile Computing (16 pages, 10 figures)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.14726">arXiv:2409.14726</a> <span> [<a href="https://arxiv.org/pdf/2409.14726">pdf</a>, <a href="https://arxiv.org/format/2409.14726">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Emerging Technologies">cs.ET</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Semantic Communication Enabled 6G-NTN Framework: A Novel Denoising and Gateway Hop Integration Mechanism </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+X">Loc X. Nguyen</a>, <a href="/search/cs?searchtype=author&query=Hassan%2C+S+S">Sheikh Salman Hassan</a>, <a href="/search/cs?searchtype=author&query=Tun%2C+Y+K">Yan Kyaw Tun</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+K">Kitae Kim</a>, <a href="/search/cs?searchtype=author&query=Han%2C+Z">Zhu Han</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.14726v1-abstract-short" style="display: inline;"> The sixth-generation (6G) non-terrestrial networks (NTNs) are crucial for real-time monitoring in critical applications like disaster relief. However, limited bandwidth, latency, rain attenuation, long propagation delays, and co-channel interference pose challenges to efficient satellite communication. Therefore, semantic communication (SC) has emerged as a promising solution to improve transmissi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.14726v1-abstract-full').style.display = 'inline'; document.getElementById('2409.14726v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.14726v1-abstract-full" style="display: none;"> The sixth-generation (6G) non-terrestrial networks (NTNs) are crucial for real-time monitoring in critical applications like disaster relief. However, limited bandwidth, latency, rain attenuation, long propagation delays, and co-channel interference pose challenges to efficient satellite communication. Therefore, semantic communication (SC) has emerged as a promising solution to improve transmission efficiency and address these issues. In this paper, we explore the potential of SC as a bandwidth-efficient, latency-minimizing strategy specifically suited to 6G satellite communications. While existing SC methods have demonstrated efficacy in direct satellite-terrestrial transmissions, they encounter limitations in satellite networks due to distortion accumulation across gateway hop-relays. Additionally, certain ground users (GUs) experience poor signal-to-noise ratios (SNR), making direct satellite communication challenging. To address these issues, we propose a novel framework that optimizes gateway hop-relay selection for GUs with low SNR and integrates gateway-based denoising mechanisms to ensure high-quality-of-service (QoS) in satellite-based SC networks. This approach directly mitigates distortion, leading to significant improvements in satellite service performance by delivering customized services tailored to the unique signal conditions of each GU. Our findings represent a critical advancement in reliable and efficient data transmission from the Earth observation satellites, thereby enabling fast and effective responses to urgent events. Simulation results demonstrate that our proposed strategy significantly enhances overall network performance, outperforming conventional methods by offering tailored communication services based on specific GU conditions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.14726v1-abstract-full').style.display = 'none'; document.getElementById('2409.14726v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">13 pages, 8 figures, 2 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.13527">arXiv:2409.13527</a> <span> [<a href="https://arxiv.org/pdf/2409.13527">pdf</a>, <a href="https://arxiv.org/format/2409.13527">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Boosting Federated Domain Generalization: Understanding the Role of Advanced Pre-Trained Architectures </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Raha%2C+A+D">Avi Deb Raha</a>, <a href="/search/cs?searchtype=author&query=Adhikary%2C+A">Apurba Adhikary</a>, <a href="/search/cs?searchtype=author&query=Gain%2C+M">Mrityunjoy Gain</a>, <a href="/search/cs?searchtype=author&query=Qiao%2C+Y">Yu Qiao</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.13527v3-abstract-short" style="display: inline;"> In this study, we explore the efficacy of advanced pre-trained architectures, such as Vision Transformers (ViT), ConvNeXt, and Swin Transformers in enhancing Federated Domain Generalization. These architectures capture global contextual features and model long-range dependencies, making them promising candidates for improving cross-domain generalization. We conduct a broad study with in-depth anal… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.13527v3-abstract-full').style.display = 'inline'; document.getElementById('2409.13527v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.13527v3-abstract-full" style="display: none;"> In this study, we explore the efficacy of advanced pre-trained architectures, such as Vision Transformers (ViT), ConvNeXt, and Swin Transformers in enhancing Federated Domain Generalization. These architectures capture global contextual features and model long-range dependencies, making them promising candidates for improving cross-domain generalization. We conduct a broad study with in-depth analysis and systematically evaluate different variants of these architectures, using extensive pre-training datasets such as ImageNet-1K, ImageNet-21K, JFT-300M, and ImageNet-22K. Additionally, we compare self-supervised and supervised pre-training strategies to assess their impact on FDG performance. Our findings suggest that self-supervised techniques, which focus on reconstructing masked image patches, can better capture the intrinsic structure of images, thereby outperforming their supervised counterparts. Comprehensive evaluations on the Office-Home and PACS datasets demonstrate that adopting advanced architectures pre-trained on larger datasets establishes new benchmarks, achieving average accuracies of 84.46\% and 92.55\%, respectively. Additionally, we observe that certain variants of these advanced models, despite having fewer parameters, outperform larger ResNet models. This highlights the critical role of utilizing sophisticated architectures and diverse pre-training strategies to enhance FDG performance, especially in scenarios with limited computational resources where model efficiency is crucial. Our results indicate that federated learning systems can become more adaptable and efficient by leveraging these advanced methods, offering valuable insights for future research in FDG. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.13527v3-abstract-full').style.display = 'none'; document.getElementById('2409.13527v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.12860">arXiv:2408.12860</a> <span> [<a href="https://arxiv.org/pdf/2408.12860">pdf</a>, <a href="https://arxiv.org/format/2408.12860">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Active STAR-RIS Empowered Edge System for Enhanced Energy Efficiency and Task Management </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Aung%2C+P+S">Pyae Sone Aung</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+K">Kitae Kim</a>, <a href="/search/cs?searchtype=author&query=Tun%2C+Y+K">Yan Kyaw Tun</a>, <a href="/search/cs?searchtype=author&query=Han%2C+Z">Zhu Han</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.12860v1-abstract-short" style="display: inline;"> The proliferation of data-intensive and low-latency applications has driven the development of multi-access edge computing (MEC) as a viable solution to meet the increasing demands for high-performance computing and storage capabilities at the network edge. Despite the benefits of MEC, challenges such as obstructions cause non-line-of-sight (NLoS) communication to persist. Reconfigurable intellige… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.12860v1-abstract-full').style.display = 'inline'; document.getElementById('2408.12860v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.12860v1-abstract-full" style="display: none;"> The proliferation of data-intensive and low-latency applications has driven the development of multi-access edge computing (MEC) as a viable solution to meet the increasing demands for high-performance computing and storage capabilities at the network edge. Despite the benefits of MEC, challenges such as obstructions cause non-line-of-sight (NLoS) communication to persist. Reconfigurable intelligent surfaces (RISs) and the more advanced simultaneously transmitting and reflecting (STAR)-RISs have emerged to address these challenges; however, practical limitations and multiplicative fading effects hinder their efficacy. We propose an active STAR-RIS-assisted MEC system to overcome these obstacles, leveraging the advantages of active STAR-RIS. The main contributions consist of formulating an optimization problem to minimize energy consumption with task queue stability by jointly optimizing the partial task offloading, amplitude, phase shift coefficients, amplification coefficients, transmit power of the base station (BS), and admitted tasks. Furthermore, we decompose the non-convex problem into manageable sub-problems, employing sequential fractional programming for transmit power control, convex optimization technique for task offloading, and Lyapunov optimization with double deep Q-network (DDQN) for joint amplitude, phase shift, amplification, and task admission. Extensive performance evaluations demonstrate the superiority of the proposed system over benchmark schemes, highlighting its potential for enhancing MEC system performance. Numerical results indicate that our proposed system outperforms the conventional STAR-RIS-assisted by 18.64\% and the conventional RIS-assisted system by 30.43\%, respectively. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.12860v1-abstract-full').style.display = 'none'; document.getElementById('2408.12860v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">13 pages, 10 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.03959">arXiv:2408.03959</a> <span> [<a href="https://arxiv.org/pdf/2408.03959">pdf</a>, <a href="https://arxiv.org/format/2408.03959">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Semantic Enabled 6G LEO Satellite Communication for Earth Observation: A Resource-Constrained Network Optimization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hassan%2C+S+S">Sheikh Salman Hassan</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+X">Loc X. Nguyen</a>, <a href="/search/cs?searchtype=author&query=Tun%2C+Y+K">Yan Kyaw Tun</a>, <a href="/search/cs?searchtype=author&query=Han%2C+Z">Zhu Han</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.03959v1-abstract-short" style="display: inline;"> Earth observation satellites generate large amounts of real-time data for monitoring and managing time-critical events such as disaster relief missions. This presents a major challenge for satellite-to-ground communications operating under limited bandwidth capacities. This paper explores semantic communication (SC) as a potential alternative to traditional communication methods. The rationality f… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.03959v1-abstract-full').style.display = 'inline'; document.getElementById('2408.03959v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.03959v1-abstract-full" style="display: none;"> Earth observation satellites generate large amounts of real-time data for monitoring and managing time-critical events such as disaster relief missions. This presents a major challenge for satellite-to-ground communications operating under limited bandwidth capacities. This paper explores semantic communication (SC) as a potential alternative to traditional communication methods. The rationality for adopting SC is its inherent ability to reduce communication costs and make spectrum efficient for 6G non-terrestrial networks (6G-NTNs). We focus on the critical satellite imagery downlink communications latency optimization for Earth observation through SC techniques. We formulate the latency minimization problem with SC quality-of-service (SC-QoS) constraints and address this problem with a meta-heuristic discrete whale optimization algorithm (DWOA) and a one-to-one matching game. The proposed approach for captured image processing and transmission includes the integration of joint semantic and channel encoding to ensure downlink sum-rate optimization and latency minimization. Empirical results from experiments demonstrate the efficiency of the proposed framework for latency optimization while preserving high-quality data transmission when compared to baselines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.03959v1-abstract-full').style.display = 'none'; document.getElementById('2408.03959v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted in GLOBECOM 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.15426">arXiv:2407.15426</a> <span> [<a href="https://arxiv.org/pdf/2407.15426">pdf</a>, <a href="https://arxiv.org/format/2407.15426">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Resource-Efficient Federated Multimodal Learning via Layer-wise and Progressive Training </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tun%2C+Y+L">Ye Lin Tun</a>, <a href="/search/cs?searchtype=author&query=Thwal%2C+C+M">Chu Myaet Thwal</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+M+N+H">Minh N. H. Nguyen</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.15426v2-abstract-short" style="display: inline;"> Combining different data modalities enables deep neural networks to tackle complex tasks more effectively, making multimodal learning increasingly popular. To harness multimodal data closer to end users, it is essential to integrate multimodal learning with privacy-preserving approaches like federated learning (FL). However, compared to conventional unimodal learning, multimodal setting requires d… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.15426v2-abstract-full').style.display = 'inline'; document.getElementById('2407.15426v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.15426v2-abstract-full" style="display: none;"> Combining different data modalities enables deep neural networks to tackle complex tasks more effectively, making multimodal learning increasingly popular. To harness multimodal data closer to end users, it is essential to integrate multimodal learning with privacy-preserving approaches like federated learning (FL). However, compared to conventional unimodal learning, multimodal setting requires dedicated encoders for each modality, resulting in larger and more complex models. Training these models requires significant resources, presenting a substantial challenge for FL clients operating with limited computation and communication resources. To address these challenges, we introduce LW-FedMML, a layer-wise federated multimodal learning approach which decomposes the training process into multiple stages. Each stage focuses on training only a portion of the model, thereby significantly reducing the memory and computational requirements. Moreover, FL clients only need to exchange the trained model portion with the central server, lowering the resulting communication cost. We conduct extensive experiments across various FL and multimodal learning settings to validate the effectiveness of our proposed method. The results demonstrate that LW-FedMML can compete with conventional end-to-end federated multimodal learning (FedMML) while significantly reducing the resource burden on FL clients. Specifically, LW-FedMML reduces memory usage by up to $2.7\times$, computational operations (FLOPs) by $2.4\times$, and total communication cost by $2.3\times$. We also explore a progressive training approach called Prog-FedMML. While it offers lesser resource efficiency than LW-FedMML, Prog-FedMML has the potential to surpass the performance of end-to-end FedMML, making it a viable option for scenarios with fewer resource constraints. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.15426v2-abstract-full').style.display = 'none'; document.getElementById('2407.15426v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.07421">arXiv:2407.07421</a> <span> [<a href="https://arxiv.org/pdf/2407.07421">pdf</a>, <a href="https://arxiv.org/format/2407.07421">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/TNET.2024.3423780">10.1109/TNET.2024.3423780 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Federated PCA on Grassmann Manifold for IoT Anomaly Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+T">Tung-Anh Nguyen</a>, <a href="/search/cs?searchtype=author&query=Le%2C+L+T">Long Tan Le</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+T+D">Tuan Dung Nguyen</a>, <a href="/search/cs?searchtype=author&query=Bao%2C+W">Wei Bao</a>, <a href="/search/cs?searchtype=author&query=Seneviratne%2C+S">Suranga Seneviratne</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N+H">Nguyen H. Tran</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.07421v1-abstract-short" style="display: inline;"> With the proliferation of the Internet of Things (IoT) and the rising interconnectedness of devices, network security faces significant challenges, especially from anomalous activities. While traditional machine learning-based intrusion detection systems (ML-IDS) effectively employ supervised learning methods, they possess limitations such as the requirement for labeled data and challenges with hi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.07421v1-abstract-full').style.display = 'inline'; document.getElementById('2407.07421v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.07421v1-abstract-full" style="display: none;"> With the proliferation of the Internet of Things (IoT) and the rising interconnectedness of devices, network security faces significant challenges, especially from anomalous activities. While traditional machine learning-based intrusion detection systems (ML-IDS) effectively employ supervised learning methods, they possess limitations such as the requirement for labeled data and challenges with high dimensionality. Recent unsupervised ML-IDS approaches such as AutoEncoders and Generative Adversarial Networks (GAN) offer alternative solutions but pose challenges in deployment onto resource-constrained IoT devices and in interpretability. To address these concerns, this paper proposes a novel federated unsupervised anomaly detection framework, FedPCA, that leverages Principal Component Analysis (PCA) and the Alternating Directions Method Multipliers (ADMM) to learn common representations of distributed non-i.i.d. datasets. Building on the FedPCA framework, we propose two algorithms, FEDPE in Euclidean space and FEDPG on Grassmann manifolds. Our approach enables real-time threat detection and mitigation at the device level, enhancing network resilience while ensuring privacy. Moreover, the proposed algorithms are accompanied by theoretical convergence rates even under a subsampling scheme, a novel result. Experimental results on the UNSW-NB15 and TON-IoT datasets show that our proposed methods offer performance in anomaly detection comparable to nonlinear baselines, while providing significant improvements in communication and memory efficiency, underscoring their potential for securing IoT networks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.07421v1-abstract-full').style.display = 'none'; document.getElementById('2407.07421v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted for publication at IEEE/ACM Transactions on Networking</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> IEEE/ACM Transactions on Networking On page(s): 1-16 Print ISSN: 1063-6692 Online ISSN: 1558-2566 Digital Object Identifier: 10.1109/TNET.2024.3423780 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.16937">arXiv:2406.16937</a> <span> [<a href="https://arxiv.org/pdf/2406.16937">pdf</a>, <a href="https://arxiv.org/format/2406.16937">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> A Complete Survey on LLM-based AI Chatbots </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Dam%2C+S+K">Sumit Kumar Dam</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a>, <a href="/search/cs?searchtype=author&query=Qiao%2C+Y">Yu Qiao</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chaoning Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.16937v2-abstract-short" style="display: inline;"> The past few decades have witnessed an upsurge in data, forming the foundation for data-hungry, learning-based AI technology. Conversational agents, often referred to as AI chatbots, rely heavily on such data to train large language models (LLMs) and generate new content (knowledge) in response to user prompts. With the advent of OpenAI's ChatGPT, LLM-based chatbots have set new standards in the A… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.16937v2-abstract-full').style.display = 'inline'; document.getElementById('2406.16937v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.16937v2-abstract-full" style="display: none;"> The past few decades have witnessed an upsurge in data, forming the foundation for data-hungry, learning-based AI technology. Conversational agents, often referred to as AI chatbots, rely heavily on such data to train large language models (LLMs) and generate new content (knowledge) in response to user prompts. With the advent of OpenAI's ChatGPT, LLM-based chatbots have set new standards in the AI community. This paper presents a complete survey of the evolution and deployment of LLM-based chatbots in various sectors. We first summarize the development of foundational chatbots, followed by the evolution of LLMs, and then provide an overview of LLM-based chatbots currently in use and those in the development phase. Recognizing AI chatbots as tools for generating new knowledge, we explore their diverse applications across various industries. We then discuss the open challenges, considering how the data used to train the LLMs and the misuse of the generated knowledge can cause several issues. Finally, we explore the future outlook to augment their efficiency and reliability in numerous applications. By addressing key milestones and the present-day context of LLM-based chatbots, our survey invites readers to delve deeper into this realm, reflecting on how their next generation will reshape conversational AI. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.16937v2-abstract-full').style.display = 'none'; document.getElementById('2406.16937v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 17 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">23 pages, 10 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.13280">arXiv:2406.13280</a> <span> [<a href="https://arxiv.org/pdf/2406.13280">pdf</a>, <a href="https://arxiv.org/format/2406.13280">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Design Optimization of NOMA Aided Multi-STAR-RIS for Indoor Environments: A Convex Approximation Imitated Reinforcement Learning Approach </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Park%2C+Y+M">Yu Min Park</a>, <a href="/search/cs?searchtype=author&query=Hassan%2C+S+S">Sheikh Salman Hassan</a>, <a href="/search/cs?searchtype=author&query=Tun%2C+Y+K">Yan Kyaw Tun</a>, <a href="/search/cs?searchtype=author&query=Huh%2C+E">Eui-Nam Huh</a>, <a href="/search/cs?searchtype=author&query=Saad%2C+W">Walid Saad</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.13280v2-abstract-short" style="display: inline;"> Non-orthogonal multiple access (NOMA) enables multiple users to share the same frequency band, and simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) provides 360-degree full-space coverage, optimizing both transmission and reflection for improved network performance and dynamic control of the indoor environment. However, deploying STAR-RIS indoors presents ch… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.13280v2-abstract-full').style.display = 'inline'; document.getElementById('2406.13280v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.13280v2-abstract-full" style="display: none;"> Non-orthogonal multiple access (NOMA) enables multiple users to share the same frequency band, and simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) provides 360-degree full-space coverage, optimizing both transmission and reflection for improved network performance and dynamic control of the indoor environment. However, deploying STAR-RIS indoors presents challenges in interference mitigation, power consumption, and real-time configuration. In this work, a novel network architecture utilizing multiple access points (APs), STAR-RISs, and NOMA is proposed for indoor communication. To address these, we formulate an optimization problem involving user assignment, access point (AP) beamforming, and STAR-RIS phase control. A decomposition approach is used to solve the complex problem efficiently, employing a many-to-one matching algorithm for user-AP assignment and K-means clustering for resource management. Additionally, multi-agent deep reinforcement learning (MADRL) is leveraged to optimize the control of the STAR-RIS. Within the proposed MADRL framework, a novel approach is introduced in which each decision variable acts as an independent agent, enabling collaborative learning and decision making. The MADRL framework is enhanced by incorporating convex approximation (CA), which accelerates policy learning through suboptimal solutions from successive convex approximation (SCA), leading to faster adaptation and convergence. Simulations demonstrate significant improvements in network utility compared to baseline approaches. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.13280v2-abstract-full').style.display = 'none'; document.getElementById('2406.13280v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 19 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">37 pages, 11 figures. arXiv admin note: text overlap with arXiv:2311.08708</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.03773">arXiv:2406.03773</a> <span> [<a href="https://arxiv.org/pdf/2406.03773">pdf</a>, <a href="https://arxiv.org/format/2406.03773">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/LCOMM.2024.3499956">10.1109/LCOMM.2024.3499956 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Optimizing Multi-User Semantic Communication via Transfer Learning and Knowledge Distillation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+X">Loc X. Nguyen</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+K">Kitae Kim</a>, <a href="/search/cs?searchtype=author&query=Tun%2C+Y+L">Ye Lin Tun</a>, <a href="/search/cs?searchtype=author&query=Hassan%2C+S+S">Sheikh Salman Hassan</a>, <a href="/search/cs?searchtype=author&query=Tun%2C+Y+K">Yan Kyaw Tun</a>, <a href="/search/cs?searchtype=author&query=Han%2C+Z">Zhu Han</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.03773v1-abstract-short" style="display: inline;"> Semantic communication, notable for ensuring quality of service by jointly optimizing source and channel coding, effectively extracts data semantics, reduces transmission length, and mitigates channel noise. However, most studies overlook multi-user scenarios and resource availability, limiting real-world application. This paper addresses this gap by focusing on downlink communication from a base… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.03773v1-abstract-full').style.display = 'inline'; document.getElementById('2406.03773v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.03773v1-abstract-full" style="display: none;"> Semantic communication, notable for ensuring quality of service by jointly optimizing source and channel coding, effectively extracts data semantics, reduces transmission length, and mitigates channel noise. However, most studies overlook multi-user scenarios and resource availability, limiting real-world application. This paper addresses this gap by focusing on downlink communication from a base station to multiple users with varying computing capacities. Users employ variants of Swin transformer models for source decoding and a simple architecture for channel decoding. We propose a novel training regimen, incorporating transfer learning and knowledge distillation to improve low-computing users' performance. Extensive simulations validate the proposed methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.03773v1-abstract-full').style.display = 'none'; document.getElementById('2406.03773v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">5 pages, 5 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> in IEEE Communications Letters, vol. 29, no. 1, pp. 90-94, Jan. 2025 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.02000">arXiv:2406.02000</a> <span> [<a href="https://arxiv.org/pdf/2406.02000">pdf</a>, <a href="https://arxiv.org/format/2406.02000">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Advancing Ultra-Reliable 6G: Transformer and Semantic Localization Empowered Robust Beamforming in Millimeter-Wave Communications </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Raha%2C+A+D">Avi Deb Raha</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+K">Kitae Kim</a>, <a href="/search/cs?searchtype=author&query=Adhikary%2C+A">Apurba Adhikary</a>, <a href="/search/cs?searchtype=author&query=Gain%2C+M">Mrityunjoy Gain</a>, <a href="/search/cs?searchtype=author&query=Han%2C+Z">Zhu Han</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.02000v3-abstract-short" style="display: inline;"> Advancements in 6G wireless technology have elevated the importance of beamforming, especially for attaining ultra-high data rates via millimeter-wave (mmWave) frequency deployment. Although promising, mmWave bands require substantial beam training to achieve precise beamforming. While initial deep learning models that use RGB camera images demonstrated promise in reducing beam training overhead,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.02000v3-abstract-full').style.display = 'inline'; document.getElementById('2406.02000v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.02000v3-abstract-full" style="display: none;"> Advancements in 6G wireless technology have elevated the importance of beamforming, especially for attaining ultra-high data rates via millimeter-wave (mmWave) frequency deployment. Although promising, mmWave bands require substantial beam training to achieve precise beamforming. While initial deep learning models that use RGB camera images demonstrated promise in reducing beam training overhead, their performance suffers due to sensitivity to lighting and environmental variations. Due to this sensitivity, Quality of Service (QoS) fluctuates, eventually affecting the stability and dependability of networks in dynamic environments. This emphasizes a critical need for robust solutions. This paper proposes a robust beamforming technique to ensure consistent QoS under varying environmental conditions. An optimization problem has been formulated to maximize users' data rates. To solve the formulated NP-hard optimization problem, we decompose it into two subproblems: the semantic localization problem and the optimal beam selection problem. To solve the semantic localization problem, we propose a novel method that leverages the K-means clustering and YOLOv8 model. To solve the beam selection problem, we propose a novel lightweight hybrid architecture that combines a lightweight transformer with a CNN architecture through a weighted entropy mechanism. This hybrid architecture utilizes multimodal data sources to dynamically predict the optimal beams. A novel metric, Accuracy-Complexity Efficiency (ACE), has been proposed to quantify this. Six testing scenarios have been developed to evaluate the robustness of the proposed model. Finally, the simulation result demonstrates that the proposed model outperforms several state-of-the-art baselines regarding beam prediction accuracy, received power, and ACE in the developed test scenarios. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.02000v3-abstract-full').style.display = 'none'; document.getElementById('2406.02000v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.00431">arXiv:2406.00431</a> <span> [<a href="https://arxiv.org/pdf/2406.00431">pdf</a>, <a href="https://arxiv.org/ps/2406.00431">ps</a>, <a href="https://arxiv.org/format/2406.00431">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> SpaFL: Communication-Efficient Federated Learning with Sparse Models and Low computational Overhead </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kim%2C+M">Minsu Kim</a>, <a href="/search/cs?searchtype=author&query=Saad%2C+W">Walid Saad</a>, <a href="/search/cs?searchtype=author&query=Debbah%2C+M">Merouane Debbah</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.00431v2-abstract-short" style="display: inline;"> The large communication and computation overhead of federated learning (FL) is one of the main challenges facing its practical deployment over resource-constrained clients and systems. In this work, SpaFL: a communication-efficient FL framework is proposed to optimize sparse model structures with low computational overhead. In SpaFL, a trainable threshold is defined for each filter/neuron to prune… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.00431v2-abstract-full').style.display = 'inline'; document.getElementById('2406.00431v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.00431v2-abstract-full" style="display: none;"> The large communication and computation overhead of federated learning (FL) is one of the main challenges facing its practical deployment over resource-constrained clients and systems. In this work, SpaFL: a communication-efficient FL framework is proposed to optimize sparse model structures with low computational overhead. In SpaFL, a trainable threshold is defined for each filter/neuron to prune its all connected parameters, thereby leading to structured sparsity. To optimize the pruning process itself, only thresholds are communicated between a server and clients instead of parameters, thereby learning how to prune. Further, global thresholds are used to update model parameters by extracting aggregated parameter importance. The generalization bound of SpaFL is also derived, thereby proving key insights on the relation between sparsity and performance. Experimental results show that SpaFL improves accuracy while requiring much less communication and computing resources compared to sparse baselines. The code is available at https://github.com/news-vt/SpaFL_NeruIPS_2024 <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.00431v2-abstract-full').style.display = 'none'; document.getElementById('2406.00431v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 1 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Published in NeurIPS 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.19771">arXiv:2405.19771</a> <span> [<a href="https://arxiv.org/pdf/2405.19771">pdf</a>, <a href="https://arxiv.org/format/2405.19771">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Data Service Maximization in Space-Air-Ground Integrated 6G Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ei%2C+N+N">Nway Nway Ei</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+K">Kitae Kim</a>, <a href="/search/cs?searchtype=author&query=Tun%2C+Y+K">Yan Kyaw Tun</a>, <a href="/search/cs?searchtype=author&query=Han%2C+Z">Zhu Han</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2405.19771v2-abstract-short" style="display: inline;"> Integrating terrestrial and non-terrestrial networks has emerged as a promising paradigm to fulfill the constantly growing demand for connectivity, low transmission delay, and quality of services (QoS). This integration brings together the strengths of the reliability of terrestrial networks, broad coverage and service continuity of non-terrestrial networks like low earth orbit satellites (LEOSats… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.19771v2-abstract-full').style.display = 'inline'; document.getElementById('2405.19771v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.19771v2-abstract-full" style="display: none;"> Integrating terrestrial and non-terrestrial networks has emerged as a promising paradigm to fulfill the constantly growing demand for connectivity, low transmission delay, and quality of services (QoS). This integration brings together the strengths of the reliability of terrestrial networks, broad coverage and service continuity of non-terrestrial networks like low earth orbit satellites (LEOSats), etc. In this work, we study a data service maximization problem in space-air-ground integrated network (SAGIN) where the ground base stations (GBSs) and LEOSats cooperatively serve the coexisting aerial users (AUs) and ground users (GUs). Then, by considering the spectrum scarcity, interference, and QoS requirements of the users, we jointly optimize the user association, AU's trajectory, and power allocation. To tackle the formulated mixed-integer non-convex problem, we disintegrate it into two subproblems: 1) user association problem and 2) trajectory and power allocation problem. We formulate the user association problem as a binary integer programming problem and solve it by using the Gurobi optimizer. Meanwhile, the trajectory and power allocation problem is solved by the deep deterministic policy gradient (DDPG) method to cope with the problem's non-convexity and dynamic network environments. Then, the two subproblems are alternately solved by the proposed block coordinate descent algorithm. By comparing with the baselines in the existing literature, extensive simulations are conducted to evaluate the performance of the proposed framework. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.19771v2-abstract-full').style.display = 'none'; document.getElementById('2405.19771v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 30 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">5 pages, 4 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.15230">arXiv:2405.15230</a> <span> [<a href="https://arxiv.org/pdf/2405.15230">pdf</a>, <a href="https://arxiv.org/format/2405.15230">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> $i$REPO: $i$mplicit Reward Pairwise Difference based Empirical Preference Optimization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Le%2C+L+T">Long Tan Le</a>, <a href="/search/cs?searchtype=author&query=Shu%2C+H">Han Shu</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+T">Tung-Anh Nguyen</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N+H">Nguyen H. Tran</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2405.15230v2-abstract-short" style="display: inline;"> While astonishingly capable, large Language Models (LLM) can sometimes produce outputs that deviate from human expectations. Such deviations necessitate an alignment phase to prevent disseminating untruthful, toxic, or biased information. Traditional alignment methods based on reinforcement learning often struggle with the identified instability, whereas preference optimization methods are limited… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.15230v2-abstract-full').style.display = 'inline'; document.getElementById('2405.15230v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.15230v2-abstract-full" style="display: none;"> While astonishingly capable, large Language Models (LLM) can sometimes produce outputs that deviate from human expectations. Such deviations necessitate an alignment phase to prevent disseminating untruthful, toxic, or biased information. Traditional alignment methods based on reinforcement learning often struggle with the identified instability, whereas preference optimization methods are limited by their overfitting to pre-collected hard-label datasets. In this paper, we propose a novel LLM alignment framework named $i$REPO, which utilizes implicit Reward pairwise difference regression for Empirical Preference Optimization. Particularly, $i$REPO employs self-generated datasets labeled by empirical human (or AI annotator) preference to iteratively refine the aligned policy through a novel regression-based loss function. Furthermore, we introduce an innovative algorithm backed by theoretical guarantees for achieving optimal results under ideal assumptions and providing a practical performance-gap result without such assumptions. Experimental results with Phi-2 and Mistral-7B demonstrate that $i$REPO effectively achieves self-alignment using soft-label, self-generated responses and the logit of empirical AI annotators. Furthermore, our approach surpasses preference optimization baselines in evaluations using the Language Model Evaluation Harness and Multi-turn benchmarks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.15230v2-abstract-full').style.display = 'none'; document.getElementById('2405.15230v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Under Review</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.09259">arXiv:2404.09259</a> <span> [<a href="https://arxiv.org/pdf/2404.09259">pdf</a>, <a href="https://arxiv.org/format/2404.09259">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> FedCCL: Federated Dual-Clustered Feature Contrast Under Domain Heterogeneity </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Qiao%2C+Y">Yu Qiao</a>, <a href="/search/cs?searchtype=author&query=Le%2C+H+Q">Huy Q. Le</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+M">Mengchun Zhang</a>, <a href="/search/cs?searchtype=author&query=Adhikary%2C+A">Apurba Adhikary</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chaoning Zhang</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.09259v2-abstract-short" style="display: inline;"> Federated learning (FL) facilitates a privacy-preserving neural network training paradigm through collaboration between edge clients and a central server. One significant challenge is that the distributed data is not independently and identically distributed (non-IID), typically including both intra-domain and inter-domain heterogeneity. However, recent research is limited to simply using averaged… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.09259v2-abstract-full').style.display = 'inline'; document.getElementById('2404.09259v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.09259v2-abstract-full" style="display: none;"> Federated learning (FL) facilitates a privacy-preserving neural network training paradigm through collaboration between edge clients and a central server. One significant challenge is that the distributed data is not independently and identically distributed (non-IID), typically including both intra-domain and inter-domain heterogeneity. However, recent research is limited to simply using averaged signals as a form of regularization and only focusing on one aspect of these non-IID challenges. Given these limitations, this paper clarifies these two non-IID challenges and attempts to introduce cluster representation to address them from both local and global perspectives. Specifically, we propose a dual-clustered feature contrast-based FL framework with dual focuses. First, we employ clustering on the local representations of each client, aiming to capture intra-class information based on these local clusters at a high level of granularity. Then, we facilitate cross-client knowledge sharing by pulling the local representation closer to clusters shared by clients with similar semantics while pushing them away from clusters with dissimilar semantics. Second, since the sizes of local clusters belonging to the same class may differ for each client, we further utilize clustering on the global side and conduct averaging to create a consistent global signal for guiding each local training in a contrastive manner. Experimental results on multiple datasets demonstrate that our proposal achieves comparable or superior performance gain under intra-domain and inter-domain heterogeneity. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.09259v2-abstract-full').style.display = 'none'; document.getElementById('2404.09259v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 14 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">This work was accepted by Information Fusion Journal</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.06776">arXiv:2404.06776</a> <span> [<a href="https://arxiv.org/pdf/2404.06776">pdf</a>, <a href="https://arxiv.org/format/2404.06776">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Logit Calibration and Feature Contrast for Robust Federated Learning on Non-IID Data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Qiao%2C+Y">Yu Qiao</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chaoning Zhang</a>, <a href="/search/cs?searchtype=author&query=Adhikary%2C+A">Apurba Adhikary</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.06776v1-abstract-short" style="display: inline;"> Federated learning (FL) is a privacy-preserving distributed framework for collaborative model training on devices in edge networks. However, challenges arise due to vulnerability to adversarial examples (AEs) and the non-independent and identically distributed (non-IID) nature of data distribution among devices, hindering the deployment of adversarially robust and accurate learning models at the e… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.06776v1-abstract-full').style.display = 'inline'; document.getElementById('2404.06776v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.06776v1-abstract-full" style="display: none;"> Federated learning (FL) is a privacy-preserving distributed framework for collaborative model training on devices in edge networks. However, challenges arise due to vulnerability to adversarial examples (AEs) and the non-independent and identically distributed (non-IID) nature of data distribution among devices, hindering the deployment of adversarially robust and accurate learning models at the edge. While adversarial training (AT) is commonly acknowledged as an effective defense strategy against adversarial attacks in centralized training, we shed light on the adverse effects of directly applying AT in FL that can severely compromise accuracy, especially in non-IID challenges. Given this limitation, this paper proposes FatCC, which incorporates local logit \underline{C}alibration and global feature \underline{C}ontrast into the vanilla federated adversarial training (\underline{FAT}) process from both logit and feature perspectives. This approach can effectively enhance the federated system's robust accuracy (RA) and clean accuracy (CA). First, we propose logit calibration, where the logits are calibrated during local adversarial updates, thereby improving adversarial robustness. Second, FatCC introduces feature contrast, which involves a global alignment term that aligns each local representation with unbiased global features, thus further enhancing robustness and accuracy in federated adversarial environments. Extensive experiments across multiple datasets demonstrate that FatCC achieves comparable or superior performance gains in both CA and RA compared to other baselines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.06776v1-abstract-full').style.display = 'none'; document.getElementById('2404.06776v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.05131">arXiv:2403.05131</a> <span> [<a href="https://arxiv.org/pdf/2403.05131">pdf</a>, <a href="https://arxiv.org/format/2403.05131">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Sora as an AGI World Model? A Complete Survey on Text-to-Video Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Cho%2C+J">Joseph Cho</a>, <a href="/search/cs?searchtype=author&query=Puspitasari%2C+F+D">Fachrina Dewi Puspitasari</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+S">Sheng Zheng</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+J">Jingyao Zheng</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+L">Lik-Hang Lee</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+T">Tae-Ho Kim</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chaoning Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.05131v2-abstract-short" style="display: inline;"> The evolution of video generation from text, starting with animating MNIST numbers to simulating the physical world with Sora, has progressed at a breakneck speed over the past seven years. While often seen as a superficial expansion of the predecessor text-to-image generation model, text-to-video generation models are developed upon carefully engineered constituents. Here, we systematically discu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.05131v2-abstract-full').style.display = 'inline'; document.getElementById('2403.05131v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.05131v2-abstract-full" style="display: none;"> The evolution of video generation from text, starting with animating MNIST numbers to simulating the physical world with Sora, has progressed at a breakneck speed over the past seven years. While often seen as a superficial expansion of the predecessor text-to-image generation model, text-to-video generation models are developed upon carefully engineered constituents. Here, we systematically discuss these elements consisting of but not limited to core building blocks (vision, language, and temporal) and supporting features from the perspective of their contributions to achieving a world model. We employ the PRISMA framework to curate 97 impactful research articles from renowned scientific databases primarily studying video synthesis using text conditions. Upon minute exploration of these manuscripts, we observe that text-to-video generation involves more intricate technologies beyond the plain extension of text-to-image generation. Our additional review into the shortcomings of Sora-generated videos pinpoints the call for more in-depth studies in various enabling aspects of video generation such as dataset, evaluation metric, efficient architecture, and human-controlled generation. Finally, we conclude that the study of the text-to-video generation may still be in its infancy, requiring contribution from the cross-discipline research community towards its advancement as the first step to realize artificial general intelligence (AGI). <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.05131v2-abstract-full').style.display = 'none'; document.getElementById('2403.05131v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 8 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">First complete survey on Text-to-Video Generation, 44 pages, 20 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.02803">arXiv:2403.02803</a> <span> [<a href="https://arxiv.org/pdf/2403.02803">pdf</a>, <a href="https://arxiv.org/format/2403.02803">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Towards Robust Federated Learning via Logits Calibration on Non-IID Data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Qiao%2C+Y">Yu Qiao</a>, <a href="/search/cs?searchtype=author&query=Adhikary%2C+A">Apurba Adhikary</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chaoning Zhang</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.02803v1-abstract-short" style="display: inline;"> Federated learning (FL) is a privacy-preserving distributed management framework based on collaborative model training of distributed devices in edge networks. However, recent studies have shown that FL is vulnerable to adversarial examples (AEs), leading to a significant drop in its performance. Meanwhile, the non-independent and identically distributed (non-IID) challenge of data distribution be… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.02803v1-abstract-full').style.display = 'inline'; document.getElementById('2403.02803v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.02803v1-abstract-full" style="display: none;"> Federated learning (FL) is a privacy-preserving distributed management framework based on collaborative model training of distributed devices in edge networks. However, recent studies have shown that FL is vulnerable to adversarial examples (AEs), leading to a significant drop in its performance. Meanwhile, the non-independent and identically distributed (non-IID) challenge of data distribution between edge devices can further degrade the performance of models. Consequently, both AEs and non-IID pose challenges to deploying robust learning models at the edge. In this work, we adopt the adversarial training (AT) framework to improve the robustness of FL models against adversarial example (AE) attacks, which can be termed as federated adversarial training (FAT). Moreover, we address the non-IID challenge by implementing a simple yet effective logits calibration strategy under the FAT framework, which can enhance the robustness of models when subjected to adversarial attacks. Specifically, we employ a direct strategy to adjust the logits output by assigning higher weights to classes with small samples during training. This approach effectively tackles the class imbalance in the training data, with the goal of mitigating biases between local and global models. Experimental results on three dataset benchmarks, MNIST, Fashion-MNIST, and CIFAR-10 show that our strategy achieves competitive results in natural and robust accuracy compared to several baselines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.02803v1-abstract-full').style.display = 'none'; document.getElementById('2403.02803v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by IEEE NOMS 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.06638">arXiv:2402.06638</a> <span> [<a href="https://arxiv.org/pdf/2402.06638">pdf</a>, <a href="https://arxiv.org/format/2402.06638">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Statistical Finance">q-fin.ST</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/ICOIN56518.2023.10048928">10.1109/ICOIN56518.2023.10048928 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Transformers with Attentive Federated Aggregation for Time Series Stock Forecasting </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Thwal%2C+C+M">Chu Myaet Thwal</a>, <a href="/search/cs?searchtype=author&query=Tun%2C+Y+L">Ye Lin Tun</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+K">Kitae Kim</a>, <a href="/search/cs?searchtype=author&query=Park%2C+S">Seong-Bae Park</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.06638v1-abstract-short" style="display: inline;"> Recent innovations in transformers have shown their superior performance in natural language processing (NLP) and computer vision (CV). The ability to capture long-range dependencies and interactions in sequential data has also triggered a great interest in time series modeling, leading to the widespread use of transformers in many time series applications. However, being the most common and cruci… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.06638v1-abstract-full').style.display = 'inline'; document.getElementById('2402.06638v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.06638v1-abstract-full" style="display: none;"> Recent innovations in transformers have shown their superior performance in natural language processing (NLP) and computer vision (CV). The ability to capture long-range dependencies and interactions in sequential data has also triggered a great interest in time series modeling, leading to the widespread use of transformers in many time series applications. However, being the most common and crucial application, the adaptation of transformers to time series forecasting has remained limited, with both promising and inconsistent results. In contrast to the challenges in NLP and CV, time series problems not only add the complexity of order or temporal dependence among input sequences but also consider trend, level, and seasonality information that much of this data is valuable for decision making. The conventional training scheme has shown deficiencies regarding model overfitting, data scarcity, and privacy issues when working with transformers for a forecasting task. In this work, we propose attentive federated transformers for time series stock forecasting with better performance while preserving the privacy of participating enterprises. Empirical results on various stock data from the Yahoo! Finance website indicate the superiority of our proposed scheme in dealing with the above challenges and data heterogeneity in federated learning. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.06638v1-abstract-full').style.display = 'none'; document.getElementById('2402.06638v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Published in IEEE ICOIN 2023</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.13898">arXiv:2401.13898</a> <span> [<a href="https://arxiv.org/pdf/2401.13898">pdf</a>, <a href="https://arxiv.org/format/2401.13898">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Cross-Modal Prototype based Multimodal Federated Learning under Severely Missing Modality </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Le%2C+H+Q">Huy Q. Le</a>, <a href="/search/cs?searchtype=author&query=Thwal%2C+C+M">Chu Myaet Thwal</a>, <a href="/search/cs?searchtype=author&query=Qiao%2C+Y">Yu Qiao</a>, <a href="/search/cs?searchtype=author&query=Tun%2C+Y+L">Ye Lin Tun</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+M+N+H">Minh N. H. Nguyen</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2401.13898v1-abstract-short" style="display: inline;"> Multimodal federated learning (MFL) has emerged as a decentralized machine learning paradigm, allowing multiple clients with different modalities to collaborate on training a machine learning model across diverse data sources without sharing their private data. However, challenges, such as data heterogeneity and severely missing modalities, pose crucial hindrances to the robustness of MFL, signifi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.13898v1-abstract-full').style.display = 'inline'; document.getElementById('2401.13898v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.13898v1-abstract-full" style="display: none;"> Multimodal federated learning (MFL) has emerged as a decentralized machine learning paradigm, allowing multiple clients with different modalities to collaborate on training a machine learning model across diverse data sources without sharing their private data. However, challenges, such as data heterogeneity and severely missing modalities, pose crucial hindrances to the robustness of MFL, significantly impacting the performance of global model. The absence of a modality introduces misalignment during the local training phase, stemming from zero-filling in the case of clients with missing modalities. Consequently, achieving robust generalization in global model becomes imperative, especially when dealing with clients that have incomplete data. In this paper, we propose Multimodal Federated Cross Prototype Learning (MFCPL), a novel approach for MFL under severely missing modalities by conducting the complete prototypes to provide diverse modality knowledge in modality-shared level with the cross-modal regularization and modality-specific level with cross-modal contrastive mechanism. Additionally, our approach introduces the cross-modal alignment to provide regularization for modality-specific features, thereby enhancing overall performance, particularly in scenarios involving severely missing modalities. Through extensive experiments on three multimodal datasets, we demonstrate the effectiveness of MFCPL in mitigating these challenges and improving the overall performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.13898v1-abstract-full').style.display = 'none'; document.getElementById('2401.13898v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">12 pages, 8 figures, 5 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.11736">arXiv:2401.11736</a> <span> [<a href="https://arxiv.org/pdf/2401.11736">pdf</a>, <a href="https://arxiv.org/format/2401.11736">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/BigComp51126.2021.00035">10.1109/BigComp51126.2021.00035 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Attention on Personalized Clinical Decision Support System: Federated Learning Approach </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Thwal%2C+C+M">Chu Myaet Thwal</a>, <a href="/search/cs?searchtype=author&query=Thar%2C+K">Kyi Thar</a>, <a href="/search/cs?searchtype=author&query=Tun%2C+Y+L">Ye Lin Tun</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2401.11736v1-abstract-short" style="display: inline;"> Health management has become a primary problem as new kinds of diseases and complex symptoms are introduced to a rapidly growing modern society. Building a better and smarter healthcare infrastructure is one of the ultimate goals of a smart city. To the best of our knowledge, neural network models are already employed to assist healthcare professionals in achieving this goal. Typically, training a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.11736v1-abstract-full').style.display = 'inline'; document.getElementById('2401.11736v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.11736v1-abstract-full" style="display: none;"> Health management has become a primary problem as new kinds of diseases and complex symptoms are introduced to a rapidly growing modern society. Building a better and smarter healthcare infrastructure is one of the ultimate goals of a smart city. To the best of our knowledge, neural network models are already employed to assist healthcare professionals in achieving this goal. Typically, training a neural network requires a rich amount of data but heterogeneous and vulnerable properties of clinical data introduce a challenge for the traditional centralized network. Moreover, adding new inputs to a medical database requires re-training an existing model from scratch. To tackle these challenges, we proposed a deep learning-based clinical decision support system trained and managed under a federated learning paradigm. We focused on a novel strategy to guarantee the safety of patient privacy and overcome the risk of cyberattacks while enabling large-scale clinical data mining. As a result, we can leverage rich clinical data for training each local neural network without the need for exchanging the confidential data of patients. Moreover, we implemented the proposed scheme as a sequence-to-sequence model architecture integrating the attention mechanism. Thus, our objective is to provide a personalized clinical decision support system with evolvable characteristics that can deliver accurate solutions and assist healthcare professionals in medical diagnosing. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.11736v1-abstract-full').style.display = 'none'; document.getElementById('2401.11736v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Published in IEEE BigComp 2021</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.11652">arXiv:2401.11652</a> <span> [<a href="https://arxiv.org/pdf/2401.11652">pdf</a>, <a href="https://arxiv.org/format/2401.11652">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1016/j.neunet.2023.11.044">10.1016/j.neunet.2023.11.044 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> OnDev-LCT: On-Device Lightweight Convolutional Transformers towards federated learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Thwal%2C+C+M">Chu Myaet Thwal</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+M+N+H">Minh N. H. Nguyen</a>, <a href="/search/cs?searchtype=author&query=Tun%2C+Y+L">Ye Lin Tun</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+S+T">Seong Tae Kim</a>, <a href="/search/cs?searchtype=author&query=Thai%2C+M+T">My T. Thai</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2401.11652v1-abstract-short" style="display: inline;"> Federated learning (FL) has emerged as a promising approach to collaboratively train machine learning models across multiple edge devices while preserving privacy. The success of FL hinges on the efficiency of participating models and their ability to handle the unique challenges of distributed learning. While several variants of Vision Transformer (ViT) have shown great potential as alternatives… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.11652v1-abstract-full').style.display = 'inline'; document.getElementById('2401.11652v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.11652v1-abstract-full" style="display: none;"> Federated learning (FL) has emerged as a promising approach to collaboratively train machine learning models across multiple edge devices while preserving privacy. The success of FL hinges on the efficiency of participating models and their ability to handle the unique challenges of distributed learning. While several variants of Vision Transformer (ViT) have shown great potential as alternatives to modern convolutional neural networks (CNNs) for centralized training, the unprecedented size and higher computational demands hinder their deployment on resource-constrained edge devices, challenging their widespread application in FL. Since client devices in FL typically have limited computing resources and communication bandwidth, models intended for such devices must strike a balance between model size, computational efficiency, and the ability to adapt to the diverse and non-IID data distributions encountered in FL. To address these challenges, we propose OnDev-LCT: Lightweight Convolutional Transformers for On-Device vision tasks with limited training data and resources. Our models incorporate image-specific inductive biases through the LCT tokenizer by leveraging efficient depthwise separable convolutions in residual linear bottleneck blocks to extract local features, while the multi-head self-attention (MHSA) mechanism in the LCT encoder implicitly facilitates capturing global representations of images. Extensive experiments on benchmark image datasets indicate that our models outperform existing lightweight vision models while having fewer parameters and lower computational demands, making them suitable for FL scenarios with data heterogeneity and communication bottlenecks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.11652v1-abstract-full').style.display = 'none'; document.getElementById('2401.11652v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Published in Neural Networks</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.11647">arXiv:2401.11647</a> <span> [<a href="https://arxiv.org/pdf/2401.11647">pdf</a>, <a href="https://arxiv.org/format/2401.11647">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> LW-FedSSL: Resource-efficient Layer-wise Federated Self-supervised Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tun%2C+Y+L">Ye Lin Tun</a>, <a href="/search/cs?searchtype=author&query=Thwal%2C+C+M">Chu Myaet Thwal</a>, <a href="/search/cs?searchtype=author&query=Huy%2C+L+Q">Le Quang Huy</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+M+N+H">Minh N. H. Nguyen</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2401.11647v3-abstract-short" style="display: inline;"> Many studies integrate federated learning (FL) with self-supervised learning (SSL) to take advantage of raw data distributed across edge devices. However, edge devices often struggle with high computation and communication costs imposed by SSL and FL algorithms. To tackle this hindrance, we propose LW-FedSSL, a layer-wise federated self-supervised learning approach that allows edge devices to incr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.11647v3-abstract-full').style.display = 'inline'; document.getElementById('2401.11647v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.11647v3-abstract-full" style="display: none;"> Many studies integrate federated learning (FL) with self-supervised learning (SSL) to take advantage of raw data distributed across edge devices. However, edge devices often struggle with high computation and communication costs imposed by SSL and FL algorithms. To tackle this hindrance, we propose LW-FedSSL, a layer-wise federated self-supervised learning approach that allows edge devices to incrementally train a single layer of the model at a time. We introduce server-side calibration and representation alignment mechanisms to ensure LW-FedSSL delivers performance on par with conventional federated self-supervised learning (FedSSL) while significantly lowering resource demands. In a pure layer-wise training scheme, training one layer at a time may limit effective interaction between different layers of the model. The server-side calibration mechanism takes advantage of the resource-rich FL server to ensure smooth collaboration between different layers of the global model. During local training, the representation alignment mechanism encourages closeness between representations of local models and those of the global model, thereby preserving the layer cohesion established by server-side calibration. With the proposed mechanisms, LW-FedSSL achieves a $3.3 \times$ reduction in memory usage, $2.1 \times$ fewer computational operations (FLOPs), and a $3.2 \times$ lower communication cost while maintaining the same level of performance as its end-to-end training counterpart. Additionally, we explore a progressive training strategy called Prog-FedSSL, which matches end-to-end training in memory requirements but offers a $1.8 \times$ reduction in FLOPs and communication costs. Although Prog-FedSSL is not as resource-efficient as LW-FedSSL, its performance improvements make it a suitable candidate for FL environments with more lenient resource constraints. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.11647v3-abstract-full').style.display = 'none'; document.getElementById('2401.11647v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 21 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.11419">arXiv:2401.11419</a> <span> [<a href="https://arxiv.org/pdf/2401.11419">pdf</a>, <a href="https://arxiv.org/format/2401.11419">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Joint UAV Deployment and Resource Allocation in THz-Assisted MEC-Enabled Integrated Space-Air-Ground Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tun%2C+Y+K">Yan Kyaw Tun</a>, <a href="/search/cs?searchtype=author&query=D%C3%A1n%2C+G">Gy枚rgy D谩n</a>, <a href="/search/cs?searchtype=author&query=Park%2C+Y+M">Yu Min Park</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2401.11419v1-abstract-short" style="display: inline;"> Multi-access edge computing (MEC)-enabled integrated space-air-ground (SAG) networks have drawn much attention recently, as they can provide communication and computing services to wireless devices in areas that lack terrestrial base stations (TBSs). Leveraging the ample bandwidth in the terahertz (THz) spectrum, in this paper, we propose MEC-enabled integrated SAG networks with collaboration amon… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.11419v1-abstract-full').style.display = 'inline'; document.getElementById('2401.11419v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.11419v1-abstract-full" style="display: none;"> Multi-access edge computing (MEC)-enabled integrated space-air-ground (SAG) networks have drawn much attention recently, as they can provide communication and computing services to wireless devices in areas that lack terrestrial base stations (TBSs). Leveraging the ample bandwidth in the terahertz (THz) spectrum, in this paper, we propose MEC-enabled integrated SAG networks with collaboration among unmanned aerial vehicles (UAVs). We then formulate the problem of minimizing the energy consumption of devices and UAVs in the proposed MEC-enabled integrated SAG networks by optimizing tasks offloading decisions, THz sub-bands assignment, transmit power control, and UAVs deployment. The formulated problem is a mixed-integer nonlinear programming (MILP) problem with a non-convex structure, which is challenging to solve. We thus propose a block coordinate descent (BCD) approach to decompose the problem into four sub-problems: 1) device task offloading decision problem, 2) THz sub-band assignment and power control problem, 3) UAV deployment problem, and 4) UAV task offloading decision problem. We then propose to use a matching game, concave-convex procedure (CCP) method, successive convex approximation (SCA), and block successive upper-bound minimization (BSUM) approaches for solving the individual subproblems. Finally, extensive simulations are performed to demonstrate the effectiveness of our proposed algorithm. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.11419v1-abstract-full').style.display = 'none'; document.getElementById('2401.11419v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">36 pages, 8 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.09579">arXiv:2312.09579</a> <span> [<a href="https://arxiv.org/pdf/2312.09579">pdf</a>, <a href="https://arxiv.org/format/2312.09579">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> MobileSAMv2: Faster Segment Anything to Everything </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chaoning Zhang</a>, <a href="/search/cs?searchtype=author&query=Han%2C+D">Dongshen Han</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+S">Sheng Zheng</a>, <a href="/search/cs?searchtype=author&query=Choi%2C+J">Jinwoo Choi</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+T">Tae-Ho Kim</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2312.09579v1-abstract-short" style="display: inline;"> Segment anything model (SAM) addresses two practical yet challenging segmentation tasks: \textbf{segment anything (SegAny)}, which utilizes a certain point to predict the mask for a single object of interest, and \textbf{segment everything (SegEvery)}, which predicts the masks for all objects on the image. What makes SegAny slow for SAM is its heavyweight image encoder, which has been addressed by… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.09579v1-abstract-full').style.display = 'inline'; document.getElementById('2312.09579v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.09579v1-abstract-full" style="display: none;"> Segment anything model (SAM) addresses two practical yet challenging segmentation tasks: \textbf{segment anything (SegAny)}, which utilizes a certain point to predict the mask for a single object of interest, and \textbf{segment everything (SegEvery)}, which predicts the masks for all objects on the image. What makes SegAny slow for SAM is its heavyweight image encoder, which has been addressed by MobileSAM via decoupled knowledge distillation. The efficiency bottleneck of SegEvery with SAM, however, lies in its mask decoder because it needs to first generate numerous masks with redundant grid-search prompts and then perform filtering to obtain the final valid masks. We propose to improve its efficiency by directly generating the final masks with only valid prompts, which can be obtained through object discovery. Our proposed approach not only helps reduce the total time on the mask decoder by at least 16 times but also achieves superior performance. Specifically, our approach yields an average performance boost of 3.6\% (42.5\% \textit{v.s.} 38.9\%) for zero-shot object proposal on the LVIS dataset with the mask AR@$K$ metric. Qualitative results show that our approach generates fine-grained masks while avoiding over-segmenting things. This project targeting faster SegEvery than the original SAM is termed MobileSAMv2 to differentiate from MobileSAM which targets faster SegAny. Moreover, we demonstrate that our new prompt sampling is also compatible with the distilled image encoders in MobileSAM, contributing to a unified framework for efficient SegAny and SegEvery. The code is available at the same link as MobileSAM Project \href{https://github.com/ChaoningZhang/MobileSAM}{\textcolor{red}{https://github.com/ChaoningZhang/MobileSAM}}. \end{abstract} <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.09579v1-abstract-full').style.display = 'none'; document.getElementById('2312.09579v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">MobileSAM achieves faster segment anything, while MobileSAMv2 achieves faster segment everything</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.08714">arXiv:2312.08714</a> <span> [<a href="https://arxiv.org/pdf/2312.08714">pdf</a>, <a href="https://arxiv.org/format/2312.08714">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Aerial STAR-RIS Empowered MEC: A DRL Approach for Energy Minimization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Aung%2C+P+S">Pyae Sone Aung</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+X">Loc X. Nguyen</a>, <a href="/search/cs?searchtype=author&query=Tun%2C+Y+K">Yan Kyaw Tun</a>, <a href="/search/cs?searchtype=author&query=Han%2C+Z">Zhu Han</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2312.08714v1-abstract-short" style="display: inline;"> Multi-access Edge Computing (MEC) addresses computational and battery limitations in devices by allowing them to offload computation tasks. To overcome the difficulties in establishing line-of-sight connections, integrating unmanned aerial vehicles (UAVs) has proven beneficial, offering enhanced data exchange, rapid deployment, and mobility. The utilization of reconfigurable intelligent surfaces (… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.08714v1-abstract-full').style.display = 'inline'; document.getElementById('2312.08714v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.08714v1-abstract-full" style="display: none;"> Multi-access Edge Computing (MEC) addresses computational and battery limitations in devices by allowing them to offload computation tasks. To overcome the difficulties in establishing line-of-sight connections, integrating unmanned aerial vehicles (UAVs) has proven beneficial, offering enhanced data exchange, rapid deployment, and mobility. The utilization of reconfigurable intelligent surfaces (RIS), specifically simultaneously transmitting and reflecting RIS (STAR-RIS) technology, further extends coverage capabilities and introduces flexibility in MEC. This study explores the integration of UAV and STAR-RIS to facilitate communication between IoT devices and an MEC server. The formulated problem aims to minimize energy consumption for IoT devices and aerial STAR-RIS by jointly optimizing task offloading, aerial STAR-RIS trajectory, amplitude and phase shift coefficients, and transmit power. Given the non-convexity of the problem and the dynamic environment, solving it directly within a polynomial time frame is challenging. Therefore, deep reinforcement learning (DRL), particularly proximal policy optimization (PPO), is introduced for its sample efficiency and stability. Simulation results illustrate the effectiveness of the proposed system compared to benchmark schemes in the literature. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.08714v1-abstract-full').style.display = 'none'; document.getElementById('2312.08714v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2311.16538">arXiv:2311.16538</a> <span> [<a href="https://arxiv.org/pdf/2311.16538">pdf</a>, <a href="https://arxiv.org/format/2311.16538">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> Federated Learning with Diffusion Models for Privacy-Sensitive Vision Tasks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tun%2C+Y+L">Ye Lin Tun</a>, <a href="/search/cs?searchtype=author&query=Thwal%2C+C+M">Chu Myaet Thwal</a>, <a href="/search/cs?searchtype=author&query=Yoon%2C+J+S">Ji Su Yoon</a>, <a href="/search/cs?searchtype=author&query=Kang%2C+S+M">Sun Moo Kang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chaoning Zhang</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2311.16538v1-abstract-short" style="display: inline;"> Diffusion models have shown great potential for vision-related tasks, particularly for image generation. However, their training is typically conducted in a centralized manner, relying on data collected from publicly available sources. This approach may not be feasible or practical in many domains, such as the medical field, which involves privacy concerns over data collection. Despite the challen… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.16538v1-abstract-full').style.display = 'inline'; document.getElementById('2311.16538v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2311.16538v1-abstract-full" style="display: none;"> Diffusion models have shown great potential for vision-related tasks, particularly for image generation. However, their training is typically conducted in a centralized manner, relying on data collected from publicly available sources. This approach may not be feasible or practical in many domains, such as the medical field, which involves privacy concerns over data collection. Despite the challenges associated with privacy-sensitive data, such domains could still benefit from valuable vision services provided by diffusion models. Federated learning (FL) plays a crucial role in enabling decentralized model training without compromising data privacy. Instead of collecting data, an FL system gathers model parameters, effectively safeguarding the private data of different parties involved. This makes FL systems vital for managing decentralized learning tasks, especially in scenarios where privacy-sensitive data is distributed across a network of clients. Nonetheless, FL presents its own set of challenges due to its distributed nature and privacy-preserving properties. Therefore, in this study, we explore the FL strategy to train diffusion models, paving the way for the development of federated diffusion models. We conduct experiments on various FL scenarios, and our findings demonstrate that federated diffusion models have great potential to deliver vision services to privacy-sensitive domains. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.16538v1-abstract-full').style.display = 'none'; document.getElementById('2311.16538v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2311.16535">arXiv:2311.16535</a> <span> [<a href="https://arxiv.org/pdf/2311.16535">pdf</a>, <a href="https://arxiv.org/format/2311.16535">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1016/j.neunet.2023.06.010">10.1016/j.neunet.2023.06.010 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Contrastive encoder pre-training-based clustered federated learning for heterogeneous data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tun%2C+Y+L">Ye Lin Tun</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+M+N+H">Minh N. H. Nguyen</a>, <a href="/search/cs?searchtype=author&query=Thwal%2C+C+M">Chu Myaet Thwal</a>, <a href="/search/cs?searchtype=author&query=Choi%2C+J">Jinwoo Choi</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2311.16535v1-abstract-short" style="display: inline;"> Federated learning (FL) is a promising approach that enables distributed clients to collaboratively train a global model while preserving their data privacy. However, FL often suffers from data heterogeneity problems, which can significantly affect its performance. To address this, clustered federated learning (CFL) has been proposed to construct personalized models for different client clusters.… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.16535v1-abstract-full').style.display = 'inline'; document.getElementById('2311.16535v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2311.16535v1-abstract-full" style="display: none;"> Federated learning (FL) is a promising approach that enables distributed clients to collaboratively train a global model while preserving their data privacy. However, FL often suffers from data heterogeneity problems, which can significantly affect its performance. To address this, clustered federated learning (CFL) has been proposed to construct personalized models for different client clusters. One effective client clustering strategy is to allow clients to choose their own local models from a model pool based on their performance. However, without pre-trained model parameters, such a strategy is prone to clustering failure, in which all clients choose the same model. Unfortunately, collecting a large amount of labeled data for pre-training can be costly and impractical in distributed environments. To overcome this challenge, we leverage self-supervised contrastive learning to exploit unlabeled data for the pre-training of FL systems. Together, self-supervised pre-training and client clustering can be crucial components for tackling the data heterogeneity issues of FL. Leveraging these two crucial strategies, we propose contrastive pre-training-based clustered federated learning (CP-CFL) to improve the model convergence and overall performance of FL systems. In this work, we demonstrate the effectiveness of CP-CFL through extensive experiments in heterogeneous FL settings, and present various interesting observations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.16535v1-abstract-full').style.display = 'none'; document.getElementById('2311.16535v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Published in Neural Networks</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2311.11465">arXiv:2311.11465</a> <span> [<a href="https://arxiv.org/pdf/2311.11465">pdf</a>, <a href="https://arxiv.org/format/2311.11465">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Understanding Segment Anything Model: SAM is Biased Towards Texture Rather than Shape </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chaoning Zhang</a>, <a href="/search/cs?searchtype=author&query=Qiao%2C+Y">Yu Qiao</a>, <a href="/search/cs?searchtype=author&query=Tariq%2C+S">Shehbaz Tariq</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+S">Sheng Zheng</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chenshuang Zhang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+C">Chenghao Li</a>, <a href="/search/cs?searchtype=author&query=Shin%2C+H">Hyundong Shin</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2311.11465v1-abstract-short" style="display: inline;"> In contrast to the human vision that mainly depends on the shape for recognizing the objects, deep image recognition models are widely known to be biased toward texture. Recently, Meta research team has released the first foundation model for image segmentation, termed segment anything model (SAM), which has attracted significant attention. In this work, we understand SAM from the perspective of t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.11465v1-abstract-full').style.display = 'inline'; document.getElementById('2311.11465v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2311.11465v1-abstract-full" style="display: none;"> In contrast to the human vision that mainly depends on the shape for recognizing the objects, deep image recognition models are widely known to be biased toward texture. Recently, Meta research team has released the first foundation model for image segmentation, termed segment anything model (SAM), which has attracted significant attention. In this work, we understand SAM from the perspective of texture \textit{v.s.} shape. Different from label-oriented recognition tasks, the SAM is trained to predict a mask for covering the object shape based on a promt. With this said, it seems self-evident that the SAM is biased towards shape. In this work, however, we reveal an interesting finding: the SAM is strongly biased towards texture-like dense features rather than shape. This intriguing finding is supported by a novel setup where we disentangle texture and shape cues and design texture-shape cue conflict for mask prediction. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.11465v1-abstract-full').style.display = 'none'; document.getElementById('2311.11465v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2311.08708">arXiv:2311.08708</a> <span> [<a href="https://arxiv.org/pdf/2311.08708">pdf</a>, <a href="https://arxiv.org/format/2311.08708">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> </div> </div> <p class="title is-5 mathjax"> Joint User Pairing and Beamforming Design of Multi-STAR-RISs-Aided NOMA in the Indoor Environment via Multi-Agent Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Park%2C+Y+M">Yu Min Park</a>, <a href="/search/cs?searchtype=author&query=Tun%2C+Y+K">Yan Kyaw Tun</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2311.08708v2-abstract-short" style="display: inline;"> The development of 6G/B5G wireless networks, which have requirements that go beyond current 5G networks, is gaining interest from academia and industry. However, to increase 6G/B5G network quality, conventional cellular networks that rely on terrestrial base stations are constrained geographically and economically. Meanwhile, NOMA allows multiple users to share the same resources, which improves t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.08708v2-abstract-full').style.display = 'inline'; document.getElementById('2311.08708v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2311.08708v2-abstract-full" style="display: none;"> The development of 6G/B5G wireless networks, which have requirements that go beyond current 5G networks, is gaining interest from academia and industry. However, to increase 6G/B5G network quality, conventional cellular networks that rely on terrestrial base stations are constrained geographically and economically. Meanwhile, NOMA allows multiple users to share the same resources, which improves the spectral efficiency of the system and has the advantage of supporting a larger number of users. Additionally, by intelligently manipulating the phase and amplitude of both the reflected and transmitted signals, STAR-RISs can achieve improved coverage, increased spectral efficiency, and enhanced communication reliability. However, STAR-RISs must simultaneously optimize the amplitude and phase shift corresponding to reflection and transmission, which makes the existing terrestrial networks more complicated and is considered a major challenging issue. Motivated by the above, we study the joint user pairing for NOMA and beamforming design of Multi-STAR-RISs in an indoor environment. Then, we formulate the optimization problem with the objective of maximizing the total throughput of MUs by jointly optimizing the decoding order, user pairing, active beamforming, and passive beamforming. However, the formulated problem is a MINLP. To address this challenge, we first introduce the decoding order for NOMA networks. Next, we decompose the original problem into two subproblems, namely: 1) MU pairing and 2) Beamforming optimization under the optimal decoding order. For the first subproblem, we employ correlation-based K-means clustering to solve the user pairing problem. Then, to jointly deal with beamforming vector optimizations, we propose MAPPO, which can make quick decisions in the given environment owing to its low complexity. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.08708v2-abstract-full').style.display = 'none'; document.getElementById('2311.08708v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 pages, 9 figures, IEEE/IFIP Network Operations and Management Symposium (NOMS) 2024 submitted</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.13236">arXiv:2310.13236</a> <span> [<a href="https://arxiv.org/pdf/2310.13236">pdf</a>, <a href="https://arxiv.org/format/2310.13236">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/TVT.2024.3401140">10.1109/TVT.2024.3401140 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> An Efficient Federated Learning Framework for Training Semantic Communication System </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+X">Loc X. Nguyen</a>, <a href="/search/cs?searchtype=author&query=Le%2C+H+Q">Huy Q. Le</a>, <a href="/search/cs?searchtype=author&query=Tun%2C+Y+L">Ye Lin Tun</a>, <a href="/search/cs?searchtype=author&query=Aung%2C+P+S">Pyae Sone Aung</a>, <a href="/search/cs?searchtype=author&query=Tun%2C+Y+K">Yan Kyaw Tun</a>, <a href="/search/cs?searchtype=author&query=Han%2C+Z">Zhu Han</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2310.13236v2-abstract-short" style="display: inline;"> Semantic communication has emerged as a pillar for the next generation of communication systems due to its capabilities in alleviating data redundancy. Most semantic communication systems are built upon advanced deep learning models whose training performance heavily relies on data availability. Existing studies often make unrealistic assumptions of a readily accessible data source, where in pract… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.13236v2-abstract-full').style.display = 'inline'; document.getElementById('2310.13236v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.13236v2-abstract-full" style="display: none;"> Semantic communication has emerged as a pillar for the next generation of communication systems due to its capabilities in alleviating data redundancy. Most semantic communication systems are built upon advanced deep learning models whose training performance heavily relies on data availability. Existing studies often make unrealistic assumptions of a readily accessible data source, where in practice, data is mainly created on the client side. Due to privacy and security concerns, the transmission of data is restricted, which is necessary for conventional centralized training schemes. To address this challenge, we explore semantic communication in a federated learning (FL) setting that utilizes client data without leaking privacy. Additionally, we design our system to tackle the communication overhead by reducing the quantity of information delivered in each global round. In this way, we can save significant bandwidth for resource-limited devices and reduce overall network traffic. Finally, we introduce a mechanism to aggregate the global model from clients, called FedLol. Extensive simulation results demonstrate the effectiveness of our proposed technique compared to baseline methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.13236v2-abstract-full').style.display = 'none'; document.getElementById('2310.13236v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 19 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">5 pages, 3 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> in IEEE Transactions on Vehicular Technology, vol. 73, no. 10, pp. 15872-15877, Oct. 2024 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.09021">arXiv:2310.09021</a> <span> [<a href="https://arxiv.org/pdf/2310.09021">pdf</a>, <a href="https://arxiv.org/format/2310.09021">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> </div> </div> <p class="title is-5 mathjax"> Generative AI-driven Semantic Communication Framework for NextG Wireless Network </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Raha%2C+A+D">Avi Deb Raha</a>, <a href="/search/cs?searchtype=author&query=Munir%2C+M+S">Md. Shirajum Munir</a>, <a href="/search/cs?searchtype=author&query=Adhikary%2C+A">Apurba Adhikary</a>, <a href="/search/cs?searchtype=author&query=Qiao%2C+Y">Yu Qiao</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2310.09021v1-abstract-short" style="display: inline;"> This work designs a novel semantic communication (SemCom) framework for the next-generation wireless network to tackle the challenges of unnecessary transmission of vast amounts that cause high bandwidth consumption, more latency, and experience with bad quality of services (QoS). In particular, these challenges hinder applications like intelligent transportation systems (ITS), metaverse, mixed re… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.09021v1-abstract-full').style.display = 'inline'; document.getElementById('2310.09021v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.09021v1-abstract-full" style="display: none;"> This work designs a novel semantic communication (SemCom) framework for the next-generation wireless network to tackle the challenges of unnecessary transmission of vast amounts that cause high bandwidth consumption, more latency, and experience with bad quality of services (QoS). In particular, these challenges hinder applications like intelligent transportation systems (ITS), metaverse, mixed reality, and the Internet of Everything, where real-time and efficient data transmission is paramount. Therefore, to reduce communication overhead and maintain the QoS of emerging applications such as metaverse, ITS, and digital twin creation, this work proposes a novel semantic communication framework. First, an intelligent semantic transmitter is designed to capture the meaningful information (e.g., the rode-side image in ITS) by designing a domain-specific Mobile Segment Anything Model (MSAM)-based mechanism to reduce the potential communication traffic while QoS remains intact. Second, the concept of generative AI is introduced for building the SemCom to reconstruct and denoise the received semantic data frame at the receiver end. In particular, the Generative Adversarial Network (GAN) mechanism is designed to maintain a superior quality reconstruction under different signal-to-noise (SNR) channel conditions. Finally, we have tested and evaluated the proposed semantic communication (SemCom) framework with the real-world 6G scenario of ITS; in particular, the base station equipped with an RGB camera and a mmWave phased array. Experimental results demonstrate the efficacy of the proposed SemCom framework by achieving high-quality reconstruction across various SNR channel conditions, resulting in 93.45% data reduction in communication. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.09021v1-abstract-full').style.display = 'none'; document.getElementById('2310.09021v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2309.15659">arXiv:2309.15659</a> <span> [<a href="https://arxiv.org/pdf/2309.15659">pdf</a>, <a href="https://arxiv.org/format/2309.15659">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1145/3627673.3679752">10.1145/3627673.3679752 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Federated Deep Equilibrium Learning: Harnessing Compact Global Representations to Enhance Personalization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Le%2C+L+T">Long Tan Le</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+T+D">Tuan Dung Nguyen</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+T">Tung-Anh Nguyen</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a>, <a href="/search/cs?searchtype=author&query=Seneviratne%2C+S">Suranga Seneviratne</a>, <a href="/search/cs?searchtype=author&query=Bao%2C+W">Wei Bao</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N+H">Nguyen H. Tran</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2309.15659v2-abstract-short" style="display: inline;"> Federated Learning (FL) has emerged as a groundbreaking distributed learning paradigm enabling clients to train a global model collaboratively without exchanging data. Despite enhancing privacy and efficiency in information retrieval and knowledge management contexts, training and deploying FL models confront significant challenges such as communication bottlenecks, data heterogeneity, and memory… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.15659v2-abstract-full').style.display = 'inline'; document.getElementById('2309.15659v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.15659v2-abstract-full" style="display: none;"> Federated Learning (FL) has emerged as a groundbreaking distributed learning paradigm enabling clients to train a global model collaboratively without exchanging data. Despite enhancing privacy and efficiency in information retrieval and knowledge management contexts, training and deploying FL models confront significant challenges such as communication bottlenecks, data heterogeneity, and memory limitations. To comprehensively address these challenges, we introduce FeDEQ, a novel FL framework that incorporates deep equilibrium learning and consensus optimization to harness compact global data representations for efficient personalization. Specifically, we design a unique model structure featuring an equilibrium layer for global representation extraction, followed by explicit layers tailored for local personalization. We then propose a novel FL algorithm rooted in the alternating directions method of multipliers (ADMM), which enables the joint optimization of a shared equilibrium layer and individual personalized layers across distributed datasets. Our theoretical analysis confirms that FeDEQ converges to a stationary point, achieving both compact global representations and optimal personalized parameters for each client. Extensive experiments on various benchmarks demonstrate that FeDEQ matches the performance of state-of-the-art personalized FL methods, while significantly reducing communication size by up to 4 times and memory footprint by 1.5 times during training. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.15659v2-abstract-full').style.display = 'none'; document.getElementById('2309.15659v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 27 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at CIKM 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2309.13223">arXiv:2309.13223</a> <span> [<a href="https://arxiv.org/pdf/2309.13223">pdf</a>, <a href="https://arxiv.org/format/2309.13223">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Causal Reasoning: Charting a Revolutionary Course for Next-Generation AI-Native Wireless Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Thomas%2C+C+K">Christo Kurisummoottil Thomas</a>, <a href="/search/cs?searchtype=author&query=Chaccour%2C+C">Christina Chaccour</a>, <a href="/search/cs?searchtype=author&query=Saad%2C+W">Walid Saad</a>, <a href="/search/cs?searchtype=author&query=Debbah%2C+M">Merouane Debbah</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2309.13223v3-abstract-short" style="display: inline;"> Despite the basic premise that next-generation wireless networks (e.g., 6G) will be artificial intelligence (AI)-native, to date, most existing efforts remain either qualitative or incremental extensions to existing "AI for wireless" paradigms. Indeed, creating AI-native wireless networks faces significant technical challenges due to the limitations of data-driven, training-intensive AI. These lim… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.13223v3-abstract-full').style.display = 'inline'; document.getElementById('2309.13223v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.13223v3-abstract-full" style="display: none;"> Despite the basic premise that next-generation wireless networks (e.g., 6G) will be artificial intelligence (AI)-native, to date, most existing efforts remain either qualitative or incremental extensions to existing "AI for wireless" paradigms. Indeed, creating AI-native wireless networks faces significant technical challenges due to the limitations of data-driven, training-intensive AI. These limitations include the black-box nature of the AI models, their curve-fitting nature, which can limit their ability to reason and adapt, their reliance on large amounts of training data, and the energy inefficiency of large neural networks. In response to these limitations, this article presents a comprehensive, forward-looking vision that addresses these shortcomings by introducing a novel framework for building AI-native wireless networks; grounded in the emerging field of causal reasoning. Causal reasoning, founded on causal discovery, causal representation learning, and causal inference, can help build explainable, reasoning-aware, and sustainable wireless networks. Towards fulfilling this vision, we first highlight several wireless networking challenges that can be addressed by causal discovery and representation, including ultra-reliable beamforming for terahertz (THz) systems, near-accurate physical twin modeling for digital twins, training data augmentation, and semantic communication. We showcase how incorporating causal discovery can assist in achieving dynamic adaptability, resilience, and cognition in addressing these challenges. Furthermore, we outline potential frameworks that leverage causal inference to achieve the overarching objectives of future-generation networks, including intent management, dynamic adaptability, human-level cognition, reasoning, and the critical element of time sensitivity. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.13223v3-abstract-full').style.display = 'none'; document.getElementById('2309.13223v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.13735">arXiv:2308.13735</a> <span> [<a href="https://arxiv.org/pdf/2308.13735">pdf</a>, <a href="https://arxiv.org/format/2308.13735">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> MST-compression: Compressing and Accelerating Binary Neural Networks with Minimum Spanning Tree </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Vo%2C+Q+H">Quang Hieu Vo</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+L">Linh-Tam Tran</a>, <a href="/search/cs?searchtype=author&query=Bae%2C+S">Sung-Ho Bae</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+L">Lok-Won Kim</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2308.13735v1-abstract-short" style="display: inline;"> Binary neural networks (BNNs) have been widely adopted to reduce the computational cost and memory storage on edge-computing devices by using one-bit representation for activations and weights. However, as neural networks become wider/deeper to improve accuracy and meet practical requirements, the computational burden remains a significant challenge even on the binary version. To address these iss… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.13735v1-abstract-full').style.display = 'inline'; document.getElementById('2308.13735v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.13735v1-abstract-full" style="display: none;"> Binary neural networks (BNNs) have been widely adopted to reduce the computational cost and memory storage on edge-computing devices by using one-bit representation for activations and weights. However, as neural networks become wider/deeper to improve accuracy and meet practical requirements, the computational burden remains a significant challenge even on the binary version. To address these issues, this paper proposes a novel method called Minimum Spanning Tree (MST) compression that learns to compress and accelerate BNNs. The proposed architecture leverages an observation from previous works that an output channel in a binary convolution can be computed using another output channel and XNOR operations with weights that differ from the weights of the reused channel. We first construct a fully connected graph with vertices corresponding to output channels, where the distance between two vertices is the number of different values between the weight sets used for these outputs. Then, the MST of the graph with the minimum depth is proposed to reorder output calculations, aiming to reduce computational cost and latency. Moreover, we propose a new learning algorithm to reduce the total MST distance during training. Experimental results on benchmark models demonstrate that our method achieves significant compression ratios with negligible accuracy drops, making it a promising approach for resource-constrained edge-computing devices. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.13735v1-abstract-full').style.display = 'none'; document.getElementById('2308.13735v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">11 pages, 9 figures, ICCV 2023</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.08279">arXiv:2308.08279</a> <span> [<a href="https://arxiv.org/pdf/2308.08279">pdf</a>, <a href="https://arxiv.org/ps/2308.08279">ps</a>, <a href="https://arxiv.org/format/2308.08279">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> </div> </div> <p class="title is-5 mathjax"> Deep Reinforcement Learning based Joint Spectrum Allocation and Configuration Design for STAR-RIS-Assisted V2X Communications </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Aung%2C+P+S">Pyae Sone Aung</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+X">Loc X. Nguyen</a>, <a href="/search/cs?searchtype=author&query=Tun%2C+Y+K">Yan Kyaw Tun</a>, <a href="/search/cs?searchtype=author&query=Han%2C+Z">Zhu Han</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2308.08279v1-abstract-short" style="display: inline;"> Vehicle-to-Everything (V2X) communications play a crucial role in ensuring safe and efficient modern transportation systems. However, challenges arise in scenarios with buildings, leading to signal obstruction and coverage limitations. To alleviate these challenges, reconfigurable intelligent surface (RIS) is regarded as an effective solution for communication performance by tuning passive signal… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.08279v1-abstract-full').style.display = 'inline'; document.getElementById('2308.08279v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.08279v1-abstract-full" style="display: none;"> Vehicle-to-Everything (V2X) communications play a crucial role in ensuring safe and efficient modern transportation systems. However, challenges arise in scenarios with buildings, leading to signal obstruction and coverage limitations. To alleviate these challenges, reconfigurable intelligent surface (RIS) is regarded as an effective solution for communication performance by tuning passive signal reflection. RIS has acquired prominence in 6G networks due to its improved spectral efficiency, simple deployment, and cost-effectiveness. Nevertheless, conventional RIS solutions have coverage limitations. Therefore, researchers have started focusing on the promising concept of simultaneously transmitting and reflecting RIS (STAR-RIS), which provides 360\degree coverage while utilizing the advantages of RIS technology. In this paper, a STAR-RIS-assisted V2X communication system is investigated. An optimization problem is formulated to maximize the achievable data rate for vehicle-to-infrastructure (V2I) users while satisfying the latency and reliability requirements of vehicle-to-vehicle (V2V) pairs by jointly optimizing the spectrum allocation, amplitudes, and phase shifts of STAR-RIS elements, digital beamforming vectors for V2I links, and transmit power for V2V pairs. Since it is challenging to solve in polynomial time, we decompose our problem into two sub-problems. For the first sub-problem, we model the control variables as a Markov Decision Process (MDP) and propose a combined double deep Q-network (DDQN) with an attention mechanism so that the model can potentially focus on relevant inputs. For the latter, a standard optimization-based approach is implemented to provide a real-time solution, reducing computational costs. Extensive numerical analysis is developed to demonstrate the superiority of our proposed algorithm compared to benchmark schemes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.08279v1-abstract-full').style.display = 'none'; document.getElementById('2308.08279v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">12 pages, 9 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.15469">arXiv:2307.15469</a> <span> [<a href="https://arxiv.org/pdf/2307.15469">pdf</a>, <a href="https://arxiv.org/format/2307.15469">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> SpaceRIS: LEO Satellite Coverage Maximization in 6G Sub-THz Networks by MAPPO DRL and Whale Optimization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hassan%2C+S+S">Sheikh Salman Hassan</a>, <a href="/search/cs?searchtype=author&query=Park%2C+Y+M">Yu Min Park</a>, <a href="/search/cs?searchtype=author&query=Tun%2C+Y+K">Yan Kyaw Tun</a>, <a href="/search/cs?searchtype=author&query=Saad%2C+W">Walid Saad</a>, <a href="/search/cs?searchtype=author&query=Han%2C+Z">Zhu Han</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2307.15469v1-abstract-short" style="display: inline;"> Satellite systems face a significant challenge in effectively utilizing limited communication resources to meet the demands of ground network traffic, characterized by asymmetrical spatial distribution and time-varying characteristics. Moreover, the coverage range and signal transmission distance of low Earth orbit (LEO) satellites are restricted by notable propagation attenuation, molecular absor… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.15469v1-abstract-full').style.display = 'inline'; document.getElementById('2307.15469v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.15469v1-abstract-full" style="display: none;"> Satellite systems face a significant challenge in effectively utilizing limited communication resources to meet the demands of ground network traffic, characterized by asymmetrical spatial distribution and time-varying characteristics. Moreover, the coverage range and signal transmission distance of low Earth orbit (LEO) satellites are restricted by notable propagation attenuation, molecular absorption, and space losses in sub-terahertz (THz) frequencies. This paper introduces a novel approach to maximize LEO satellite coverage by leveraging reconfigurable intelligent surfaces (RISs) within 6G sub-THz networks. The optimization objectives encompass enhancing the end-to-end data rate, optimizing satellite-remote user equipment (RUE) associations, data packet routing within satellite constellations, RIS phase shift, and ground base station (GBS) transmit power (i.e., active beamforming). The formulated joint optimization problem poses significant challenges owing to its time-varying environment, non-convex characteristics, and NP-hard complexity. To address these challenges, we propose a block coordinate descent (BCD) algorithm that integrates balanced K-means clustering, multi-agent proximal policy optimization (MAPPO) deep reinforcement learning (DRL), and whale optimization (WOA) techniques. The performance of the proposed approach is demonstrated through comprehensive simulation results, exhibiting its superiority over existing baseline methods in the literature. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.15469v1-abstract-full').style.display = 'none'; document.getElementById('2307.15469v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.13214">arXiv:2307.13214</a> <span> [<a href="https://arxiv.org/pdf/2307.13214">pdf</a>, <a href="https://arxiv.org/format/2307.13214">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> FedMEKT: Distillation-based Embedding Knowledge Transfer for Multimodal Federated Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Le%2C+H+Q">Huy Q. Le</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+M+N+H">Minh N. H. Nguyen</a>, <a href="/search/cs?searchtype=author&query=Thwal%2C+C+M">Chu Myaet Thwal</a>, <a href="/search/cs?searchtype=author&query=Qiao%2C+Y">Yu Qiao</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chaoning Zhang</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2307.13214v2-abstract-short" style="display: inline;"> Federated learning (FL) enables a decentralized machine learning paradigm for multiple clients to collaboratively train a generalized global model without sharing their private data. Most existing works simply propose typical FL systems for single-modal data, thus limiting its potential on exploiting valuable multimodal data for future personalized applications. Furthermore, the majority of FL app… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.13214v2-abstract-full').style.display = 'inline'; document.getElementById('2307.13214v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.13214v2-abstract-full" style="display: none;"> Federated learning (FL) enables a decentralized machine learning paradigm for multiple clients to collaboratively train a generalized global model without sharing their private data. Most existing works simply propose typical FL systems for single-modal data, thus limiting its potential on exploiting valuable multimodal data for future personalized applications. Furthermore, the majority of FL approaches still rely on the labeled data at the client side, which is limited in real-world applications due to the inability of self-annotation from users. In light of these limitations, we propose a novel multimodal FL framework that employs a semi-supervised learning approach to leverage the representations from different modalities. Bringing this concept into a system, we develop a distillation-based multimodal embedding knowledge transfer mechanism, namely FedMEKT, which allows the server and clients to exchange the joint knowledge of their learning models extracted from a small multimodal proxy dataset. Our FedMEKT iteratively updates the generalized global encoders with the joint embedding knowledge from the participating clients. Thereby, to address the modality discrepancy and labeled data constraint in existing FL systems, our proposed FedMEKT comprises local multimodal autoencoder learning, generalized multimodal autoencoder construction, and generalized classifier learning. Through extensive experiments on three multimodal human activity recognition datasets, we demonstrate that FedMEKT achieves superior global encoder performance on linear evaluation and guarantees user privacy for personal data and model parameters while demanding less communication cost than other baselines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.13214v2-abstract-full').style.display = 'none'; document.getElementById('2307.13214v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.10575">arXiv:2307.10575</a> <span> [<a href="https://arxiv.org/pdf/2307.10575">pdf</a>, <a href="https://arxiv.org/format/2307.10575">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Boosting Federated Learning Convergence with Prototype Regularization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Qiao%2C+Y">Yu Qiao</a>, <a href="/search/cs?searchtype=author&query=Le%2C+H+Q">Huy Q. Le</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2307.10575v1-abstract-short" style="display: inline;"> As a distributed machine learning technique, federated learning (FL) requires clients to collaboratively train a shared model with an edge server without leaking their local data. However, the heterogeneous data distribution among clients often leads to a decrease in model performance. To tackle this issue, this paper introduces a prototype-based regularization strategy to address the heterogeneit… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.10575v1-abstract-full').style.display = 'inline'; document.getElementById('2307.10575v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.10575v1-abstract-full" style="display: none;"> As a distributed machine learning technique, federated learning (FL) requires clients to collaboratively train a shared model with an edge server without leaking their local data. However, the heterogeneous data distribution among clients often leads to a decrease in model performance. To tackle this issue, this paper introduces a prototype-based regularization strategy to address the heterogeneity in the data distribution. Specifically, the regularization process involves the server aggregating local prototypes from distributed clients to generate a global prototype, which is then sent back to the individual clients to guide their local training. The experimental results on MNIST and Fashion-MNIST show that our proposal achieves improvements of 3.3% and 8.9% in average test accuracy, respectively, compared to the most popular baseline FedAvg. Furthermore, our approach has a fast convergence rate in heterogeneous settings. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.10575v1-abstract-full').style.display = 'none'; document.getElementById('2307.10575v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.03402">arXiv:2307.03402</a> <span> [<a href="https://arxiv.org/pdf/2307.03402">pdf</a>, <a href="https://arxiv.org/format/2307.03402">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/TVT.2024.3362328">10.1109/TVT.2024.3362328 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Swin Transformer-Based Dynamic Semantic Communication for Multi-User with Different Computing Capacity </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+L+X">Loc X. Nguyen</a>, <a href="/search/cs?searchtype=author&query=Tun%2C+Y+L">Ye Lin Tun</a>, <a href="/search/cs?searchtype=author&query=Tun%2C+Y+K">Yan Kyaw Tun</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+M+N+H">Minh N. H. Nguyen</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chaoning Zhang</a>, <a href="/search/cs?searchtype=author&query=Han%2C+Z">Zhu Han</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2307.03402v1-abstract-short" style="display: inline;"> Semantic communication has gained significant attention from researchers as a promising technique to replace conventional communication in the next generation of communication systems, primarily due to its ability to reduce communication costs. However, little literature has studied its effectiveness in multi-user scenarios, particularly when there are variations in the model architectures used by… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.03402v1-abstract-full').style.display = 'inline'; document.getElementById('2307.03402v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.03402v1-abstract-full" style="display: none;"> Semantic communication has gained significant attention from researchers as a promising technique to replace conventional communication in the next generation of communication systems, primarily due to its ability to reduce communication costs. However, little literature has studied its effectiveness in multi-user scenarios, particularly when there are variations in the model architectures used by users and their computing capacities. To address this issue, we explore a semantic communication system that caters to multiple users with different model architectures by using a multi-purpose transmitter at the base station (BS). Specifically, the BS in the proposed framework employs semantic and channel encoders to encode the image for transmission, while the receiver utilizes its local channel and semantic decoder to reconstruct the original image. Our joint source-channel encoder at the BS can effectively extract and compress semantic features for specific users by considering the signal-to-noise ratio (SNR) and computing capacity of the user. Based on the network status, the joint source-channel encoder at the BS can adaptively adjust the length of the transmitted signal. A longer signal ensures more information for high-quality image reconstruction for the user, while a shorter signal helps avoid network congestion. In addition, we propose a hybrid loss function for training, which enhances the perceptual details of reconstructed images. Finally, we conduct a series of extensive evaluations and ablation studies to validate the effectiveness of the proposed system. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.03402v1-abstract-full').style.display = 'none'; document.getElementById('2307.03402v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">14 pages, 10 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> in IEEE Transactions on Vehicular Technology, vol. 73, no. 6, pp. 8957-8972, June 2024 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.02663">arXiv:2307.02663</a> <span> [<a href="https://arxiv.org/pdf/2307.02663">pdf</a>, <a href="https://arxiv.org/format/2307.02663">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> Convergence of Communications, Control, and Machine Learning for Secure and Autonomous Vehicle Navigation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zeng%2C+T">Tengchan Zeng</a>, <a href="/search/cs?searchtype=author&query=Ferdowsi%2C+A">Aidin Ferdowsi</a>, <a href="/search/cs?searchtype=author&query=Semiari%2C+O">Omid Semiari</a>, <a href="/search/cs?searchtype=author&query=Saad%2C+W">Walid Saad</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2307.02663v1-abstract-short" style="display: inline;"> Connected and autonomous vehicles (CAVs) can reduce human errors in traffic accidents, increase road efficiency, and execute various tasks ranging from delivery to smart city surveillance. Reaping these benefits requires CAVs to autonomously navigate to target destinations. To this end, each CAV's navigation controller must leverage the information collected by sensors and wireless systems for dec… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.02663v1-abstract-full').style.display = 'inline'; document.getElementById('2307.02663v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.02663v1-abstract-full" style="display: none;"> Connected and autonomous vehicles (CAVs) can reduce human errors in traffic accidents, increase road efficiency, and execute various tasks ranging from delivery to smart city surveillance. Reaping these benefits requires CAVs to autonomously navigate to target destinations. To this end, each CAV's navigation controller must leverage the information collected by sensors and wireless systems for decision-making on longitudinal and lateral movements. However, enabling autonomous navigation for CAVs requires a convergent integration of communication, control, and learning systems. The goal of this article is to explicitly expose the challenges related to this convergence and propose solutions to address them in two major use cases: Uncoordinated and coordinated CAVs. In particular, challenges related to the navigation of uncoordinated CAVs include stable path tracking, robust control against cyber-physical attacks, and adaptive navigation controller design. Meanwhile, when multiple CAVs coordinate their movements during navigation, fundamental problems such as stable formation, fast collaborative learning, and distributed intrusion detection are analyzed. For both cases, solutions using the convergence of communication theory, control theory, and machine learning are proposed to enable effective and secure CAV navigation. Preliminary simulation results are provided to show the merits of proposed solutions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.02663v1-abstract-full').style.display = 'none'; document.getElementById('2307.02663v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">3 figures and 7 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.14289">arXiv:2306.14289</a> <span> [<a href="https://arxiv.org/pdf/2306.14289">pdf</a>, <a href="https://arxiv.org/format/2306.14289">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Faster Segment Anything: Towards Lightweight SAM for Mobile Applications </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chaoning Zhang</a>, <a href="/search/cs?searchtype=author&query=Han%2C+D">Dongshen Han</a>, <a href="/search/cs?searchtype=author&query=Qiao%2C+Y">Yu Qiao</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+J+U">Jung Uk Kim</a>, <a href="/search/cs?searchtype=author&query=Bae%2C+S">Sung-Ho Bae</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+S">Seungkyu Lee</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2306.14289v2-abstract-short" style="display: inline;"> Segment Anything Model (SAM) has attracted significant attention due to its impressive zero-shot transfer performance and high versatility for numerous vision applications (like image editing with fine-grained control). Many of such applications need to be run on resource-constraint edge devices, like mobile phones. In this work, we aim to make SAM mobile-friendly by replacing the heavyweight imag… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.14289v2-abstract-full').style.display = 'inline'; document.getElementById('2306.14289v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.14289v2-abstract-full" style="display: none;"> Segment Anything Model (SAM) has attracted significant attention due to its impressive zero-shot transfer performance and high versatility for numerous vision applications (like image editing with fine-grained control). Many of such applications need to be run on resource-constraint edge devices, like mobile phones. In this work, we aim to make SAM mobile-friendly by replacing the heavyweight image encoder with a lightweight one. A naive way to train such a new SAM as in the original SAM paper leads to unsatisfactory performance, especially when limited training sources are available. We find that this is mainly caused by the coupled optimization of the image encoder and mask decoder, motivated by which we propose decoupled distillation. Concretely, we distill the knowledge from the heavy image encoder (ViT-H in the original SAM) to a lightweight image encoder, which can be automatically compatible with the mask decoder in the original SAM. The training can be completed on a single GPU within less than one day, and the resulting lightweight SAM is termed MobileSAM which is more than 60 times smaller yet performs on par with the original SAM. For inference speed, With a single GPU, MobileSAM runs around 10ms per image: 8ms on the image encoder and 4ms on the mask decoder. With superior performance, our MobileSAM is around 5 times faster than the concurrent FastSAM and 7 times smaller, making it more suitable for mobile applications. Moreover, we show that MobileSAM can run relatively smoothly on CPU. The code for our project is provided at \href{https://github.com/ChaoningZhang/MobileSAM}{\textcolor{red}{MobileSAM}}), with a demo showing that MobileSAM can run relatively smoothly on CPU. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.14289v2-abstract-full').style.display = 'none'; document.getElementById('2306.14289v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 25 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">First work to make SAM lightweight for mobile applications</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.07713">arXiv:2306.07713</a> <span> [<a href="https://arxiv.org/pdf/2306.07713">pdf</a>, <a href="https://arxiv.org/format/2306.07713">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Robustness of SAM: Segment Anything Under Corruptions and Beyond </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Qiao%2C+Y">Yu Qiao</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chaoning Zhang</a>, <a href="/search/cs?searchtype=author&query=Kang%2C+T">Taegoo Kang</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+D">Donghun Kim</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chenshuang Zhang</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+C+S">Choong Seon Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2306.07713v3-abstract-short" style="display: inline;"> Segment anything model (SAM), as the name suggests, is claimed to be capable of cutting out any object and demonstrates impressive zero-shot transfer performance with the guidance of prompts. However, there is currently a lack of comprehensive evaluation regarding its robustness under various corruptions. Understanding the robustness of SAM across different corruption scenarios is crucial for its… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.07713v3-abstract-full').style.display = 'inline'; document.getElementById('2306.07713v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.07713v3-abstract-full" style="display: none;"> Segment anything model (SAM), as the name suggests, is claimed to be capable of cutting out any object and demonstrates impressive zero-shot transfer performance with the guidance of prompts. However, there is currently a lack of comprehensive evaluation regarding its robustness under various corruptions. Understanding the robustness of SAM across different corruption scenarios is crucial for its real-world deployment. Prior works show that SAM is biased towards texture (style) rather than shape, motivated by which we start by investigating its robustness against style transfer, which is synthetic corruption. Following by interpreting the effects of synthetic corruption as style changes, we proceed to conduct a comprehensive evaluation for its robustness against 15 types of common corruption. These corruptions mainly fall into categories such as digital, noise, weather, and blur, and within each corruption category, we explore 5 severity levels to simulate real-world corruption scenarios. Beyond the corruptions, we further assess the robustness of SAM against local occlusion and local adversarial patch attacks. To the best of our knowledge, our work is the first of its kind to evaluate the robustness of SAM under style change, local occlusion, and local adversarial patch attacks. Given that patch attacks visible to human eyes are easily detectable, we further assess its robustness against global adversarial attacks that are imperceptible to human eyes. Overall, this work provides a comprehensive empirical study of the robustness of SAM, evaluating its performance under various corruptions and extending the assessment to critical aspects such as local occlusion, local adversarial patch attacks, and global adversarial attacks. These evaluations yield valuable insights into the practical applicability and effectiveness of SAM in addressing real-world challenges. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.07713v3-abstract-full').style.display = 'none'; document.getElementById('2306.07713v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 13 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">The first work evaluates the robustness of SAM under various corruptions such as style transfer, local occlusion, and adversarial patch attack</span> </p> </li> </ol> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Hong%2C+C+S&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Hong%2C+C+S&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Hong%2C+C+S&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Hong%2C+C+S&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Hong%2C+C+S&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> </ul> </nav> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository