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 64 results for author: <span class="mathjax">Almeida, M</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=Almeida%2C+M">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="Almeida, M"> </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=Almeida%2C+M&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="Almeida, M"> <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=Almeida%2C+M&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Almeida%2C+M&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Almeida%2C+M&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </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/2411.02547">arXiv:2411.02547</a> <span> [<a href="https://arxiv.org/pdf/2411.02547">pdf</a>, <a href="https://arxiv.org/format/2411.02547">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</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"> Modeling Uncertainty in 3D Gaussian Splatting through Continuous Semantic Splatting </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wilson%2C+J">Joey Wilson</a>, <a href="/search/cs?searchtype=author&query=Almeida%2C+M">Marcelino Almeida</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+M">Min Sun</a>, <a href="/search/cs?searchtype=author&query=Mahajan%2C+S">Sachit Mahajan</a>, <a href="/search/cs?searchtype=author&query=Ghaffari%2C+M">Maani Ghaffari</a>, <a href="/search/cs?searchtype=author&query=Ewen%2C+P">Parker Ewen</a>, <a href="/search/cs?searchtype=author&query=Ghasemalizadeh%2C+O">Omid Ghasemalizadeh</a>, <a href="/search/cs?searchtype=author&query=Kuo%2C+C">Cheng-Hao Kuo</a>, <a href="/search/cs?searchtype=author&query=Sen%2C+A">Arnie Sen</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="2411.02547v1-abstract-short" style="display: inline;"> In this paper, we present a novel algorithm for probabilistically updating and rasterizing semantic maps within 3D Gaussian Splatting (3D-GS). Although previous methods have introduced algorithms which learn to rasterize features in 3D-GS for enhanced scene understanding, 3D-GS can fail without warning which presents a challenge for safety-critical robotic applications. To address this gap, we pro… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02547v1-abstract-full').style.display = 'inline'; document.getElementById('2411.02547v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.02547v1-abstract-full" style="display: none;"> In this paper, we present a novel algorithm for probabilistically updating and rasterizing semantic maps within 3D Gaussian Splatting (3D-GS). Although previous methods have introduced algorithms which learn to rasterize features in 3D-GS for enhanced scene understanding, 3D-GS can fail without warning which presents a challenge for safety-critical robotic applications. To address this gap, we propose a method which advances the literature of continuous semantic mapping from voxels to ellipsoids, combining the precise structure of 3D-GS with the ability to quantify uncertainty of probabilistic robotic maps. Given a set of images, our algorithm performs a probabilistic semantic update directly on the 3D ellipsoids to obtain an expectation and variance through the use of conjugate priors. We also propose a probabilistic rasterization which returns per-pixel segmentation predictions with quantifiable uncertainty. We compare our method with similar probabilistic voxel-based methods to verify our extension to 3D ellipsoids, and perform ablation studies on uncertainty quantification and temporal smoothing. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02547v1-abstract-full').style.display = 'none'; document.getElementById('2411.02547v1-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 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.15934">arXiv:2409.15934</a> <span> [<a href="https://arxiv.org/pdf/2409.15934">pdf</a>, <a href="https://arxiv.org/format/2409.15934">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> <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"> Automated test generation to evaluate tool-augmented LLMs as conversational AI agents </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Arcadinho%2C+S">Samuel Arcadinho</a>, <a href="/search/cs?searchtype=author&query=Aparicio%2C+D">David Aparicio</a>, <a href="/search/cs?searchtype=author&query=Almeida%2C+M">Mariana Almeida</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="2409.15934v2-abstract-short" style="display: inline;"> Tool-augmented LLMs are a promising approach to create AI agents that can have realistic conversations, follow procedures, and call appropriate functions. However, evaluating them is challenging due to the diversity of possible conversations, and existing datasets focus only on single interactions and function-calling. We present a test generation pipeline to evaluate LLMs as conversational AI age… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.15934v2-abstract-full').style.display = 'inline'; document.getElementById('2409.15934v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.15934v2-abstract-full" style="display: none;"> Tool-augmented LLMs are a promising approach to create AI agents that can have realistic conversations, follow procedures, and call appropriate functions. However, evaluating them is challenging due to the diversity of possible conversations, and existing datasets focus only on single interactions and function-calling. We present a test generation pipeline to evaluate LLMs as conversational AI agents. Our framework uses LLMs to generate diverse tests grounded on user-defined procedures. For that, we use intermediate graphs to limit the LLM test generator's tendency to hallucinate content that is not grounded on input procedures, and enforces high coverage of the possible conversations. Additionally, we put forward ALMITA, a manually curated dataset for evaluating AI agents in customer support, and use it to evaluate existing LLMs. Our results show that while tool-augmented LLMs perform well in single interactions, they often struggle to handle complete conversations. While our focus is on customer support, our method is general and capable of AI agents for different domains. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.15934v2-abstract-full').style.display = 'none'; document.getElementById('2409.15934v2-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 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">14 pages, 5 figures, Submitted to GenBench@EMNLP2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.15321">arXiv:2407.15321</a> <span> [<a href="https://arxiv.org/pdf/2407.15321">pdf</a>, <a href="https://arxiv.org/format/2407.15321">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</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/10.1080/01431161.2024.2384098">10.1080/01431161.2024.2384098 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Hierarchical Homogeneity-Based Superpixel Segmentation: Application to Hyperspectral Image Analysis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ayres%2C+L+C">Luciano Carvalho Ayres</a>, <a href="/search/cs?searchtype=author&query=de+Almeida%2C+S+J+M">S茅rgio Jos茅 Melo de Almeida</a>, <a href="/search/cs?searchtype=author&query=Bermudez%2C+J+C+M">Jos茅 Carlos Moreira Bermudez</a>, <a href="/search/cs?searchtype=author&query=Borsoi%2C+R+A">Ricardo Augusto Borsoi</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="2407.15321v1-abstract-short" style="display: inline;"> Hyperspectral image (HI) analysis approaches have recently become increasingly complex and sophisticated. Recently, the combination of spectral-spatial information and superpixel techniques have addressed some hyperspectral data issues, such as the higher spatial variability of spectral signatures and dimensionality of the data. However, most existing superpixel approaches do not account for speci… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.15321v1-abstract-full').style.display = 'inline'; document.getElementById('2407.15321v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.15321v1-abstract-full" style="display: none;"> Hyperspectral image (HI) analysis approaches have recently become increasingly complex and sophisticated. Recently, the combination of spectral-spatial information and superpixel techniques have addressed some hyperspectral data issues, such as the higher spatial variability of spectral signatures and dimensionality of the data. However, most existing superpixel approaches do not account for specific HI characteristics resulting from its high spectral dimension. In this work, we propose a multiscale superpixel method that is computationally efficient for processing hyperspectral data. The Simple Linear Iterative Clustering (SLIC) oversegmentation algorithm, on which the technique is based, has been extended hierarchically. Using a novel robust homogeneity testing, the proposed hierarchical approach leads to superpixels of variable sizes but with higher spectral homogeneity when compared to the classical SLIC segmentation. For validation, the proposed homogeneity-based hierarchical method was applied as a preprocessing step in the spectral unmixing and classification tasks carried out using, respectively, the Multiscale sparse Unmixing Algorithm (MUA) and the CNN-Enhanced Graph Convolutional Network (CEGCN) methods. Simulation results with both synthetic and real data show that the technique is competitive with state-of-the-art solutions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.15321v1-abstract-full').style.display = 'none'; document.getElementById('2407.15321v1-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 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/2407.07159">arXiv:2407.07159</a> <span> [<a href="https://arxiv.org/pdf/2407.07159">pdf</a>, <a href="https://arxiv.org/format/2407.07159">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> </div> </div> <p class="title is-5 mathjax"> Finding Fake News Websites in the Wild </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Araujo%2C+L">Leandro Araujo</a>, <a href="/search/cs?searchtype=author&query=Couto%2C+J+M+M">Joao M. M. Couto</a>, <a href="/search/cs?searchtype=author&query=Nery%2C+L+F">Luiz Felipe Nery</a>, <a href="/search/cs?searchtype=author&query=Rodrigues%2C+I+C">Isadora C. Rodrigues</a>, <a href="/search/cs?searchtype=author&query=Almeida%2C+J+M">Jussara M. Almeida</a>, <a href="/search/cs?searchtype=author&query=Reis%2C+J+C+S">Julio C. S. Reis</a>, <a href="/search/cs?searchtype=author&query=Benevenuto%2C+F">Fabricio Benevenuto</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="2407.07159v2-abstract-short" style="display: inline;"> The battle against the spread of misinformation on the Internet is a daunting task faced by modern society. Fake news content is primarily distributed through digital platforms, with websites dedicated to producing and disseminating such content playing a pivotal role in this complex ecosystem. Therefore, these websites are of great interest to misinformation researchers. However, obtaining a comp… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.07159v2-abstract-full').style.display = 'inline'; document.getElementById('2407.07159v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.07159v2-abstract-full" style="display: none;"> The battle against the spread of misinformation on the Internet is a daunting task faced by modern society. Fake news content is primarily distributed through digital platforms, with websites dedicated to producing and disseminating such content playing a pivotal role in this complex ecosystem. Therefore, these websites are of great interest to misinformation researchers. However, obtaining a comprehensive list of websites labeled as producers and/or spreaders of misinformation can be challenging, particularly in developing countries. In this study, we propose a novel methodology for identifying websites responsible for creating and disseminating misinformation content, which are closely linked to users who share confirmed instances of fake news on social media. We validate our approach on Twitter by examining various execution modes and contexts. Our findings demonstrate the effectiveness of the proposed methodology in identifying misinformation websites, which can aid in gaining a better understanding of this phenomenon and enabling competent entities to tackle the problem in various areas of society. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.07159v2-abstract-full').style.display = 'none'; document.getElementById('2407.07159v2-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 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">This is a preprint version of a submitted manuscript on the Brazilian Symposium on Multimedia and the Web (WebMedia)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.13099">arXiv:2406.13099</a> <span> [<a href="https://arxiv.org/pdf/2406.13099">pdf</a>, <a href="https://arxiv.org/format/2406.13099">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"> Sampling 3D Gaussian Scenes in Seconds with Latent Diffusion Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Henderson%2C+P">Paul Henderson</a>, <a href="/search/cs?searchtype=author&query=de+Almeida%2C+M">Melonie de Almeida</a>, <a href="/search/cs?searchtype=author&query=Ivanova%2C+D">Daniela Ivanova</a>, <a href="/search/cs?searchtype=author&query=Anciukevi%C4%8Dius%2C+T">Titas Anciukevi膷ius</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="2406.13099v1-abstract-short" style="display: inline;"> We present a latent diffusion model over 3D scenes, that can be trained using only 2D image data. To achieve this, we first design an autoencoder that maps multi-view images to 3D Gaussian splats, and simultaneously builds a compressed latent representation of these splats. Then, we train a multi-view diffusion model over the latent space to learn an efficient generative model. This pipeline does… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.13099v1-abstract-full').style.display = 'inline'; document.getElementById('2406.13099v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.13099v1-abstract-full" style="display: none;"> We present a latent diffusion model over 3D scenes, that can be trained using only 2D image data. To achieve this, we first design an autoencoder that maps multi-view images to 3D Gaussian splats, and simultaneously builds a compressed latent representation of these splats. Then, we train a multi-view diffusion model over the latent space to learn an efficient generative model. This pipeline does not require object masks nor depths, and is suitable for complex scenes with arbitrary camera positions. We conduct careful experiments on two large-scale datasets of complex real-world scenes -- MVImgNet and RealEstate10K. We show that our approach enables generating 3D scenes in as little as 0.2 seconds, either from scratch, from a single input view, or from sparse input views. It produces diverse and high-quality results while running an order of magnitude faster than non-latent diffusion models and earlier NeRF-based generative models <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.13099v1-abstract-full').style.display = 'none'; document.getElementById('2406.13099v1-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 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/2401.16307">arXiv:2401.16307</a> <span> [<a href="https://arxiv.org/pdf/2401.16307">pdf</a>, <a href="https://arxiv.org/format/2401.16307">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</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/10.1145/3613904.3642662">10.1145/3613904.3642662 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Momentary Stressor Logging and Reflective Visualizations: Implications for Stress Management with Wearables </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Neupane%2C+S">Sameer Neupane</a>, <a href="/search/cs?searchtype=author&query=Saha%2C+M">Mithun Saha</a>, <a href="/search/cs?searchtype=author&query=Ali%2C+N">Nasir Ali</a>, <a href="/search/cs?searchtype=author&query=Hnat%2C+T">Timothy Hnat</a>, <a href="/search/cs?searchtype=author&query=Samiei%2C+S+A">Shahin Alan Samiei</a>, <a href="/search/cs?searchtype=author&query=Nandugudi%2C+A">Anandatirtha Nandugudi</a>, <a href="/search/cs?searchtype=author&query=Almeida%2C+D+M">David M. Almeida</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+S">Santosh Kumar</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="2401.16307v1-abstract-short" style="display: inline;"> Commercial wearables from Fitbit, Garmin, and Whoop have recently introduced real-time notifications based on detecting changes in physiological responses indicating potential stress. In this paper, we investigate how these new capabilities can be leveraged to improve stress management. We developed a smartwatch app, a smartphone app, and a cloud service, and conducted a 100-day field study with 1… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.16307v1-abstract-full').style.display = 'inline'; document.getElementById('2401.16307v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.16307v1-abstract-full" style="display: none;"> Commercial wearables from Fitbit, Garmin, and Whoop have recently introduced real-time notifications based on detecting changes in physiological responses indicating potential stress. In this paper, we investigate how these new capabilities can be leveraged to improve stress management. We developed a smartwatch app, a smartphone app, and a cloud service, and conducted a 100-day field study with 122 participants who received prompts triggered by physiological responses several times a day. They were asked whether they were stressed, and if so, to log the most likely stressor. Each week, participants received new visualizations of their data to self-reflect on patterns and trends. Participants reported better awareness of their stressors, and self-initiating fourteen kinds of behavioral changes to reduce stress in their daily lives. Repeated self-reports over 14 weeks showed reductions in both stress intensity (in 26,521 momentary ratings) and stress frequency (in 1,057 weekly surveys). <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.16307v1-abstract-full').style.display = 'none'; document.getElementById('2401.16307v1-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> 29 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">In CHI '24 Proceedings of the CHI Conference on Human Factors in Computing Systems Honolulu, HI, USA</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.13161">arXiv:2401.13161</a> <span> [<a href="https://arxiv.org/pdf/2401.13161">pdf</a>, <a href="https://arxiv.org/format/2401.13161">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="Signal Processing">eess.SP</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/LGRS.2024.3358694">10.1109/LGRS.2024.3358694 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> A Generalized Multiscale Bundle-Based Hyperspectral Sparse Unmixing Algorithm </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ayres%2C+L+C">Luciano Carvalho Ayres</a>, <a href="/search/cs?searchtype=author&query=Borsoi%2C+R+A">Ricardo Augusto Borsoi</a>, <a href="/search/cs?searchtype=author&query=Bermudez%2C+J+C+M">Jos茅 Carlos Moreira Bermudez</a>, <a href="/search/cs?searchtype=author&query=de+Almeida%2C+S+J+M">S茅rgio Jos茅 Melo de Almeida</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="2401.13161v1-abstract-short" style="display: inline;"> In hyperspectral sparse unmixing, a successful approach employs spectral bundles to address the variability of the endmembers in the spatial domain. However, the regularization penalties usually employed aggregate substantial computational complexity, and the solutions are very noise-sensitive. We generalize a multiscale spatial regularization approach to solve the unmixing problem by incorporatin… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.13161v1-abstract-full').style.display = 'inline'; document.getElementById('2401.13161v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.13161v1-abstract-full" style="display: none;"> In hyperspectral sparse unmixing, a successful approach employs spectral bundles to address the variability of the endmembers in the spatial domain. However, the regularization penalties usually employed aggregate substantial computational complexity, and the solutions are very noise-sensitive. We generalize a multiscale spatial regularization approach to solve the unmixing problem by incorporating group sparsity-inducing mixed norms. Then, we propose a noise-robust method that can take advantage of the bundle structure to deal with endmember variability while ensuring inter- and intra-class sparsity in abundance estimation with reasonable computational cost. We also present a general heuristic to select the \emph{most representative} abundance estimation over multiple runs of the unmixing process, yielding a solution that is robust and highly reproducible. Experiments illustrate the robustness and consistency of the results when compared to related methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.13161v1-abstract-full').style.display = 'none'; document.getElementById('2401.13161v1-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 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/2312.13784">arXiv:2312.13784</a> <span> [<a href="https://arxiv.org/pdf/2312.13784">pdf</a>, <a href="https://arxiv.org/format/2312.13784">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Neural and Evolutionary Computing">cs.NE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> </div> </div> <p class="title is-5 mathjax"> Benchmarking Evolutionary Community Detection Algorithms in Dynamic Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Paoletti%2C+G">Giordano Paoletti</a>, <a href="/search/cs?searchtype=author&query=Gioacchini%2C+L">Luca Gioacchini</a>, <a href="/search/cs?searchtype=author&query=Mellia%2C+M">Marco Mellia</a>, <a href="/search/cs?searchtype=author&query=Vassio%2C+L">Luca Vassio</a>, <a href="/search/cs?searchtype=author&query=Almeida%2C+J+M">Jussara M. Almeida</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="2312.13784v2-abstract-short" style="display: inline;"> In dynamic complex networks, entities interact and form network communities that evolve over time. Among the many static Community Detection (CD) solutions, the modularity-based Louvain, or Greedy Modularity Algorithm (GMA), is widely employed in real-world applications due to its intuitiveness and scalability. Nevertheless, addressing CD in dynamic graphs remains an open problem, since the evolut… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.13784v2-abstract-full').style.display = 'inline'; document.getElementById('2312.13784v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.13784v2-abstract-full" style="display: none;"> In dynamic complex networks, entities interact and form network communities that evolve over time. Among the many static Community Detection (CD) solutions, the modularity-based Louvain, or Greedy Modularity Algorithm (GMA), is widely employed in real-world applications due to its intuitiveness and scalability. Nevertheless, addressing CD in dynamic graphs remains an open problem, since the evolution of the network connections may poison the identification of communities, which may be evolving at a slower pace. Hence, naively applying GMA to successive network snapshots may lead to temporal inconsistencies in the communities. Two evolutionary adaptations of GMA, sGMA and $伪$GMA, have been proposed to tackle this problem. Yet, evaluating the performance of these methods and understanding to which scenarios each one is better suited is challenging because of the lack of a comprehensive set of metrics and a consistent ground truth. To address these challenges, we propose (i) a benchmarking framework for evolutionary CD algorithms in dynamic networks and (ii) a generalised modularity-based approach (NeGMA). Our framework allows us to generate synthetic community-structured graphs and design evolving scenarios with nine basic graph transformations occurring at different rates. We evaluate performance through three metrics we define, i.e. Correctness, Delay, and Stability. Our findings reveal that $伪$GMA is well-suited for detecting intermittent transformations, but struggles with abrupt changes; sGMA achieves superior stability, but fails to detect emerging communities; and NeGMA appears a well-balanced solution, excelling in responsiveness and instantaneous transformations detection. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.13784v2-abstract-full').style.display = 'none'; document.getElementById('2312.13784v2-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 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 21 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">Accepted at the 4th Workshop on Graphs and more Complex structures for Learning and Reasoning (GCLR) at AAAI 2024</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> 4th Workshop on Graphs and more Complex structures for Learning and Reasoning (GCLR) at AAAI 2024 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2309.08647">arXiv:2309.08647</a> <span> [<a href="https://arxiv.org/pdf/2309.08647">pdf</a>, <a href="https://arxiv.org/format/2309.08647">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"> Intent Detection at Scale: Tuning a Generic Model using Relevant Intents </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Narotamo%2C+N">Nichal Narotamo</a>, <a href="/search/cs?searchtype=author&query=Aparicio%2C+D">David Aparicio</a>, <a href="/search/cs?searchtype=author&query=Mesquita%2C+T">Tiago Mesquita</a>, <a href="/search/cs?searchtype=author&query=Almeida%2C+M">Mariana Almeida</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="2309.08647v1-abstract-short" style="display: inline;"> Accurately predicting the intent of customer support requests is vital for efficient support systems, enabling agents to quickly understand messages and prioritize responses accordingly. While different approaches exist for intent detection, maintaining separate client-specific or industry-specific models can be costly and impractical as the client base expands. This work proposes a system to sc… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.08647v1-abstract-full').style.display = 'inline'; document.getElementById('2309.08647v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.08647v1-abstract-full" style="display: none;"> Accurately predicting the intent of customer support requests is vital for efficient support systems, enabling agents to quickly understand messages and prioritize responses accordingly. While different approaches exist for intent detection, maintaining separate client-specific or industry-specific models can be costly and impractical as the client base expands. This work proposes a system to scale intent predictions to various clients effectively, by combining a single generic model with a per-client list of relevant intents. Our approach minimizes training and maintenance costs while providing a personalized experience for clients, allowing for seamless adaptation to changes in their relevant intents. Furthermore, we propose a strategy for using the clients relevant intents as model features that proves to be resilient to changes in the relevant intents of clients -- a common occurrence in production environments. The final system exhibits significantly superior performance compared to industry-specific models, showcasing its flexibility and ability to cater to diverse client needs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.08647v1-abstract-full').style.display = 'none'; document.getElementById('2309.08647v1-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 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">6 pages, 6 tables, 2 figures, ICMLA 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/2308.14782">arXiv:2308.14782</a> <span> [<a href="https://arxiv.org/pdf/2308.14782">pdf</a>, <a href="https://arxiv.org/format/2308.14782">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> </div> </div> <p class="title is-5 mathjax"> Helping Fact-Checkers Identify Fake News Stories Shared through Images on WhatsApp </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Reis%2C+J+C+S">Julio C. S. Reis</a>, <a href="/search/cs?searchtype=author&query=Melo%2C+P">Philipe Melo</a>, <a href="/search/cs?searchtype=author&query=Bel%C3%A9m%2C+F">Fabiano Bel茅m</a>, <a href="/search/cs?searchtype=author&query=Murai%2C+F">Fabricio Murai</a>, <a href="/search/cs?searchtype=author&query=Almeida%2C+J+M">Jussara M. Almeida</a>, <a href="/search/cs?searchtype=author&query=Benevenuto%2C+F">Fabricio Benevenuto</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="2308.14782v1-abstract-short" style="display: inline;"> WhatsApp has introduced a novel avenue for smartphone users to engage with and disseminate news stories. The convenience of forming interest-based groups and seamlessly sharing content has rendered WhatsApp susceptible to the exploitation of misinformation campaigns. While the process of fact-checking remains a potent tool in identifying fabricated news, its efficacy falters in the face of the unp… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.14782v1-abstract-full').style.display = 'inline'; document.getElementById('2308.14782v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.14782v1-abstract-full" style="display: none;"> WhatsApp has introduced a novel avenue for smartphone users to engage with and disseminate news stories. The convenience of forming interest-based groups and seamlessly sharing content has rendered WhatsApp susceptible to the exploitation of misinformation campaigns. While the process of fact-checking remains a potent tool in identifying fabricated news, its efficacy falters in the face of the unprecedented deluge of information generated on the Internet today. In this work, we explore automatic ranking-based strategies to propose a "fakeness score" model as a means to help fact-checking agencies identify fake news stories shared through images on WhatsApp. Based on the results, we design a tool and integrate it into a real system that has been used extensively for monitoring content during the 2018 Brazilian general election. Our experimental evaluation shows that this tool can reduce by up to 40% the amount of effort required to identify 80% of the fake news in the data when compared to current mechanisms practiced by the fact-checking agencies for the selection of news stories to be checked. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.14782v1-abstract-full').style.display = 'none'; document.getElementById('2308.14782v1-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 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">This is a preprint version of an accepted manuscript on the Brazilian Symposium on Multimedia and the Web (WebMedia). Please, consider to cite it instead of this one</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.02631">arXiv:2307.02631</a> <span> [<a href="https://arxiv.org/pdf/2307.02631">pdf</a>, <a href="https://arxiv.org/format/2307.02631">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/10.3389/frai.2024.1343447">10.3389/frai.2024.1343447 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> An explainable model to support the decision about the therapy protocol for AML </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Almeida%2C+J+M">Jade M. Almeida</a>, <a href="/search/cs?searchtype=author&query=Castro%2C+G+A">Giovanna A. Castro</a>, <a href="/search/cs?searchtype=author&query=Machado-Neto%2C+J+A">Jo茫o A. Machado-Neto</a>, <a href="/search/cs?searchtype=author&query=Almeida%2C+T+A">Tiago A. Almeida</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="2307.02631v2-abstract-short" style="display: inline;"> Acute Myeloid Leukemia (AML) is one of the most aggressive types of hematological neoplasm. To support the specialists' decision about the appropriate therapy, patients with AML receive a prognostic of outcomes according to their cytogenetic and molecular characteristics, often divided into three risk categories: favorable, intermediate, and adverse. However, the current risk classification has kn… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.02631v2-abstract-full').style.display = 'inline'; document.getElementById('2307.02631v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.02631v2-abstract-full" style="display: none;"> Acute Myeloid Leukemia (AML) is one of the most aggressive types of hematological neoplasm. To support the specialists' decision about the appropriate therapy, patients with AML receive a prognostic of outcomes according to their cytogenetic and molecular characteristics, often divided into three risk categories: favorable, intermediate, and adverse. However, the current risk classification has known problems, such as the heterogeneity between patients of the same risk group and no clear definition of the intermediate risk category. Moreover, as most patients with AML receive an intermediate-risk classification, specialists often demand other tests and analyses, leading to delayed treatment and worsening of the patient's clinical condition. This paper presents the data analysis and an explainable machine-learning model to support the decision about the most appropriate therapy protocol according to the patient's survival prediction. In addition to the prediction model being explainable, the results obtained are promising and indicate that it is possible to use it to support the specialists' decisions safely. Most importantly, the findings offered in this study have the potential to open new avenues of research toward better treatments and prognostic markers. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.02631v2-abstract-full').style.display = 'none'; document.getElementById('2307.02631v2-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 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 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">Preprint of the paper accepted to be published in the Proc. of the 12th Brazilian Conference on Intelligent Systems (BRACIS'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/2306.15740">arXiv:2306.15740</a> <span> [<a href="https://arxiv.org/pdf/2306.15740">pdf</a>, <a href="https://arxiv.org/format/2306.15740">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="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> <p class="title is-5 mathjax"> Impact of User Privacy and Mobility on Edge Offloading </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Esper%2C+J+P">Jo茫o Paulo Esper</a>, <a href="/search/cs?searchtype=author&query=Achir%2C+N">Nadjib Achir</a>, <a href="/search/cs?searchtype=author&query=Cardoso%2C+K+V">Kleber Vieira Cardoso</a>, <a href="/search/cs?searchtype=author&query=Almeida%2C+J+M">Jussara M. Almeida</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="2306.15740v1-abstract-short" style="display: inline;"> Offloading high-demanding applications to the edge provides better quality of experience (QoE) for users with limited hardware devices. However, to maintain a competitive QoE, infrastructure, and service providers must adapt to users' different mobility patterns, which can be challenging, especially for location-based services (LBS). Another issue that needs to be tackled is the increasing demand… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.15740v1-abstract-full').style.display = 'inline'; document.getElementById('2306.15740v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.15740v1-abstract-full" style="display: none;"> Offloading high-demanding applications to the edge provides better quality of experience (QoE) for users with limited hardware devices. However, to maintain a competitive QoE, infrastructure, and service providers must adapt to users' different mobility patterns, which can be challenging, especially for location-based services (LBS). Another issue that needs to be tackled is the increasing demand for user privacy protection. With less (accurate) information regarding user location, preferences, and usage patterns, forecasting the performance of offloading mechanisms becomes even more challenging. This work discusses the impacts of users' privacy and mobility when offloading to the edge. Different privacy and mobility scenarios are simulated and discussed to shed light on the trade-offs (e.g., privacy protection at the cost of increased latency) among privacy protection, mobility, and offloading performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.15740v1-abstract-full').style.display = 'none'; document.getElementById('2306.15740v1-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 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">2023 Annual IEEE International Symposium on Personal, Indoor, and Mobile Radio Communications (IEEE PIMRC 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/2305.17321">arXiv:2305.17321</a> <span> [<a href="https://arxiv.org/pdf/2305.17321">pdf</a>, <a href="https://arxiv.org/format/2305.17321">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="Information Theory">cs.IT</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"> Optimal Resource Allocation with Delay Guarantees for Network Slicing in Disaggregated RAN </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rocha%2C+F+G+C">Fl谩vio G. C. Rocha</a>, <a href="/search/cs?searchtype=author&query=de+Almeida%2C+G+M+F">Gabriel M. F. de Almeida</a>, <a href="/search/cs?searchtype=author&query=Cardoso%2C+K+V">Kleber V. Cardoso</a>, <a href="/search/cs?searchtype=author&query=Both%2C+C+B">Cristiano B. Both</a>, <a href="/search/cs?searchtype=author&query=de+Rezende%2C+J+F">Jos茅 F. de Rezende</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="2305.17321v2-abstract-short" style="display: inline;"> In this article, we propose a novel formulation for the resource allocation problem of a sliced and disaggregated Radio Access Network (RAN) and its transport network. Our proposal assures an end-to-end delay bound for the Ultra-Reliable and Low-Latency Communication (URLLC) use case while jointly considering the number of admitted users, the transmission rate allocation per slice, the functional… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.17321v2-abstract-full').style.display = 'inline'; document.getElementById('2305.17321v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.17321v2-abstract-full" style="display: none;"> In this article, we propose a novel formulation for the resource allocation problem of a sliced and disaggregated Radio Access Network (RAN) and its transport network. Our proposal assures an end-to-end delay bound for the Ultra-Reliable and Low-Latency Communication (URLLC) use case while jointly considering the number of admitted users, the transmission rate allocation per slice, the functional split of RAN nodes and the routing paths in the transport network. We use deterministic network calculus theory to calculate delay along the transport network connecting disaggregated RANs deploying network functions at the Radio Unit (RU), Distributed Unit (DU), and Central Unit (CU) nodes. The maximum end-to-end delay is a constraint in the optimization-based formulation that aims to maximize Mobile Network Operator (MNO) profit, considering a cash flow analysis to model revenue and operational costs using data from one of the world's leading MNOs. The optimization model leverages a Flexible Functional Split (FFS) approach to provide a new degree of freedom to the resource allocation strategy. Simulation results reveal that, due to its non-linear nature, there is no trivial solution to the proposed optimization problem formulation. Our proposal guarantees a maximum delay for URLLC services while satisfying minimal bandwidth requirements for enhanced Mobile BroadBand (eMBB) services and maximizing the MNO's profit. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.17321v2-abstract-full').style.display = 'none'; document.getElementById('2305.17321v2-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 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 26 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 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">21 pages, 10 figures. For the associated GitHub repository, see https://github.com/LABORA-INF-UFG/paper-FGKCJ-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/2301.02760">arXiv:2301.02760</a> <span> [<a href="https://arxiv.org/pdf/2301.02760">pdf</a>, <a href="https://arxiv.org/format/2301.02760">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"> RIC-O: Efficient placement of a disaggregated and distributed RAN Intelligent Controller with dynamic clustering of radio nodes </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Almeida%2C+G+M">Gabriel M. Almeida</a>, <a href="/search/cs?searchtype=author&query=Bruno%2C+G+Z">Gustavo Z. Bruno</a>, <a href="/search/cs?searchtype=author&query=Huff%2C+A">Alexandre Huff</a>, <a href="/search/cs?searchtype=author&query=Hiltunen%2C+M">Matti Hiltunen</a>, <a href="/search/cs?searchtype=author&query=Duarte%2C+E+P">Elias P. Duarte Jr.</a>, <a href="/search/cs?searchtype=author&query=Both%2C+C+B">Cristiano B. Both</a>, <a href="/search/cs?searchtype=author&query=Cardoso%2C+K+V">Kleber V. Cardoso</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="2301.02760v1-abstract-short" style="display: inline;"> The Radio Access Network (RAN) is the segment of cellular networks that provides wireless connectivity to end-users. O-RAN Alliance has been transforming the RAN industry by proposing open RAN specifications and the programmable Non-Real-Time and Near-Real-Time RAN Intelligent Controllers (Non-RT RIC and Near-RT RIC). Both RICs provide platforms for running applications called rApps and xApps, res… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.02760v1-abstract-full').style.display = 'inline'; document.getElementById('2301.02760v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2301.02760v1-abstract-full" style="display: none;"> The Radio Access Network (RAN) is the segment of cellular networks that provides wireless connectivity to end-users. O-RAN Alliance has been transforming the RAN industry by proposing open RAN specifications and the programmable Non-Real-Time and Near-Real-Time RAN Intelligent Controllers (Non-RT RIC and Near-RT RIC). Both RICs provide platforms for running applications called rApps and xApps, respectively, to optimize the behavior of the RAN. We investigate a disaggregation strategy of the Near-RT RIC so that its components meet stringent latency requirements while presenting a cost-effective solution. We propose the novel RIC Orchestrator (RIC-O) that optimizes the deployment of the Near-RT RIC components across the cloud-edge continuum. Edge computing nodes often present limited resources and are expensive compared to cloud computing. For example, in the O-RAN Signalling Storm Protection, Near-RT RIC is expected to support end-to-end control loop latencies as low as 10ms. Therefore, performance-critical components of Near-RT RIC and certain xApps should run at the edge while other components can run on the cloud. Furthermore, RIC-O employs an efficient strategy to react to sudden changes and re-deploy components dynamically. We evaluate our proposal through analytical modeling and real-world experiments in an extended Kubernetes deployment implementing RIC-O and disaggregated Near-RT RIC. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.02760v1-abstract-full').style.display = 'none'; document.getElementById('2301.02760v1-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 January, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 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">30 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/2212.09501">arXiv:2212.09501</a> <span> [<a href="https://arxiv.org/pdf/2212.09501">pdf</a>, <a href="https://arxiv.org/format/2212.09501">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 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/TMC.2023.3255822">10.1109/TMC.2023.3255822 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> NAWQ-SR: A Hybrid-Precision NPU Engine for Efficient On-Device Super-Resolution </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Venieris%2C+S+I">Stylianos I. Venieris</a>, <a href="/search/cs?searchtype=author&query=Almeida%2C+M">Mario Almeida</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+R">Royson Lee</a>, <a href="/search/cs?searchtype=author&query=Lane%2C+N+D">Nicholas D. Lane</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="2212.09501v3-abstract-short" style="display: inline;"> In recent years, image and video delivery systems have begun integrating deep learning super-resolution (SR) approaches, leveraging their unprecedented visual enhancement capabilities while reducing reliance on networking conditions. Nevertheless, deploying these solutions on mobile devices still remains an active challenge as SR models are excessively demanding with respect to workload and memory… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.09501v3-abstract-full').style.display = 'inline'; document.getElementById('2212.09501v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2212.09501v3-abstract-full" style="display: none;"> In recent years, image and video delivery systems have begun integrating deep learning super-resolution (SR) approaches, leveraging their unprecedented visual enhancement capabilities while reducing reliance on networking conditions. Nevertheless, deploying these solutions on mobile devices still remains an active challenge as SR models are excessively demanding with respect to workload and memory footprint. Despite recent progress on on-device SR frameworks, existing systems either penalize visual quality, lead to excessive energy consumption or make inefficient use of the available resources. This work presents NAWQ-SR, a novel framework for the efficient on-device execution of SR models. Through a novel hybrid-precision quantization technique and a runtime neural image codec, NAWQ-SR exploits the multi-precision capabilities of modern mobile NPUs in order to minimize latency, while meeting user-specified quality constraints. Moreover, NAWQ-SR selectively adapts the arithmetic precision at run time to equip the SR DNN's layers with wider representational power, improving visual quality beyond what was previously possible on NPUs. Altogether, NAWQ-SR achieves an average speedup of 7.9x, 3x and 1.91x over the state-of-the-art on-device SR systems that use heterogeneous processors (MobiSR), CPU (SplitSR) and NPU (XLSR), respectively. Furthermore, NAWQ-SR delivers an average of 3.2x speedup and 0.39 dB higher PSNR over status-quo INT8 NPU designs, but most importantly mitigates the negative effects of quantization on visual quality, setting a new state-of-the-art in the attainable quality of NPU-based SR. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.09501v3-abstract-full').style.display = 'none'; document.getElementById('2212.09501v3-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 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 December, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2022. </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 the IEEE Transactions on Mobile Computing (TMC), 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/2211.11928">arXiv:2211.11928</a> <span> [<a href="https://arxiv.org/pdf/2211.11928">pdf</a>, <a href="https://arxiv.org/ps/2211.11928">ps</a>, <a href="https://arxiv.org/format/2211.11928">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> A case study of proactive auto-scaling for an ecommerce workload </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=de+Almeida%2C+M+M+S+C">Marcella Medeiros Siqueira Coutinho de Almeida</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+T+E">Thiago Emmanuel Pereira</a>, <a href="/search/cs?searchtype=author&query=Morais%2C+F">Fabio Morais</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="2211.11928v1-abstract-short" style="display: inline;"> Preliminary data obtained from a partnership between the Federal University of Campina Grande and an ecommerce company indicates that some applications have issues when dealing with variable demand. This happens because a delay in scaling resources leads to performance degradation and, in literature, is a matter usually treated by improving the auto-scaling. To better understand the current state-… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.11928v1-abstract-full').style.display = 'inline'; document.getElementById('2211.11928v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2211.11928v1-abstract-full" style="display: none;"> Preliminary data obtained from a partnership between the Federal University of Campina Grande and an ecommerce company indicates that some applications have issues when dealing with variable demand. This happens because a delay in scaling resources leads to performance degradation and, in literature, is a matter usually treated by improving the auto-scaling. To better understand the current state-of-the-art on this subject, we re-evaluate an auto-scaling algorithm proposed in the literature, in the context of ecommerce, using a long-term real workload. Experimental results show that our proactive approach is able to achieve an accuracy of up to 94 percent and led the auto-scaling to a better performance than the reactive approach currently used by the ecommerce company. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.11928v1-abstract-full').style.display = 'none'; document.getElementById('2211.11928v1-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 November, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2211.10322">arXiv:2211.10322</a> <span> [<a href="https://arxiv.org/pdf/2211.10322">pdf</a>, <a href="https://arxiv.org/format/2211.10322">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"> Understanding the double descent curve in Machine Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sa-Couto%2C+L">Luis Sa-Couto</a>, <a href="/search/cs?searchtype=author&query=Ramos%2C+J+M">Jose Miguel Ramos</a>, <a href="/search/cs?searchtype=author&query=Almeida%2C+M">Miguel Almeida</a>, <a href="/search/cs?searchtype=author&query=Wichert%2C+A">Andreas Wichert</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="2211.10322v1-abstract-short" style="display: inline;"> The theory of bias-variance used to serve as a guide for model selection when applying Machine Learning algorithms. However, modern practice has shown success with over-parameterized models that were expected to overfit but did not. This led to the proposal of the double descent curve of performance by Belkin et al. Although it seems to describe a real, representative phenomenon, the field is lack… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.10322v1-abstract-full').style.display = 'inline'; document.getElementById('2211.10322v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2211.10322v1-abstract-full" style="display: none;"> The theory of bias-variance used to serve as a guide for model selection when applying Machine Learning algorithms. However, modern practice has shown success with over-parameterized models that were expected to overfit but did not. This led to the proposal of the double descent curve of performance by Belkin et al. Although it seems to describe a real, representative phenomenon, the field is lacking a fundamental theoretical understanding of what is happening, what are the consequences for model selection and when is double descent expected to occur. In this paper we develop a principled understanding of the phenomenon, and sketch answers to these important questions. Furthermore, we report real experimental results that are correctly predicted by our proposed hypothesis. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.10322v1-abstract-full').style.display = 'none'; document.getElementById('2211.10322v1-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, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2207.03522">arXiv:2207.03522</a> <span> [<a href="https://arxiv.org/pdf/2207.03522">pdf</a>, <a href="https://arxiv.org/format/2207.03522">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="Neural and Evolutionary Computing">cs.NE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Physics and Society">physics.soc-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> TF-GNN: Graph Neural Networks in TensorFlow </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ferludin%2C+O">Oleksandr Ferludin</a>, <a href="/search/cs?searchtype=author&query=Eigenwillig%2C+A">Arno Eigenwillig</a>, <a href="/search/cs?searchtype=author&query=Blais%2C+M">Martin Blais</a>, <a href="/search/cs?searchtype=author&query=Zelle%2C+D">Dustin Zelle</a>, <a href="/search/cs?searchtype=author&query=Pfeifer%2C+J">Jan Pfeifer</a>, <a href="/search/cs?searchtype=author&query=Sanchez-Gonzalez%2C+A">Alvaro Sanchez-Gonzalez</a>, <a href="/search/cs?searchtype=author&query=Li%2C+W+L+S">Wai Lok Sibon Li</a>, <a href="/search/cs?searchtype=author&query=Abu-El-Haija%2C+S">Sami Abu-El-Haija</a>, <a href="/search/cs?searchtype=author&query=Battaglia%2C+P">Peter Battaglia</a>, <a href="/search/cs?searchtype=author&query=Bulut%2C+N">Neslihan Bulut</a>, <a href="/search/cs?searchtype=author&query=Halcrow%2C+J">Jonathan Halcrow</a>, <a href="/search/cs?searchtype=author&query=de+Almeida%2C+F+M+G">Filipe Miguel Gon莽alves de Almeida</a>, <a href="/search/cs?searchtype=author&query=Gonnet%2C+P">Pedro Gonnet</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+L">Liangze Jiang</a>, <a href="/search/cs?searchtype=author&query=Kothari%2C+P">Parth Kothari</a>, <a href="/search/cs?searchtype=author&query=Lattanzi%2C+S">Silvio Lattanzi</a>, <a href="/search/cs?searchtype=author&query=Linhares%2C+A">Andr茅 Linhares</a>, <a href="/search/cs?searchtype=author&query=Mayer%2C+B">Brandon Mayer</a>, <a href="/search/cs?searchtype=author&query=Mirrokni%2C+V">Vahab Mirrokni</a>, <a href="/search/cs?searchtype=author&query=Palowitch%2C+J">John Palowitch</a>, <a href="/search/cs?searchtype=author&query=Paradkar%2C+M">Mihir Paradkar</a>, <a href="/search/cs?searchtype=author&query=She%2C+J">Jennifer She</a>, <a href="/search/cs?searchtype=author&query=Tsitsulin%2C+A">Anton Tsitsulin</a>, <a href="/search/cs?searchtype=author&query=Villela%2C+K">Kevin Villela</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+L">Lisa Wang</a> , et al. (2 additional authors not shown) </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="2207.03522v2-abstract-short" style="display: inline;"> TensorFlow-GNN (TF-GNN) is a scalable library for Graph Neural Networks in TensorFlow. It is designed from the bottom up to support the kinds of rich heterogeneous graph data that occurs in today's information ecosystems. In addition to enabling machine learning researchers and advanced developers, TF-GNN offers low-code solutions to empower the broader developer community in graph learning. Many… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.03522v2-abstract-full').style.display = 'inline'; document.getElementById('2207.03522v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2207.03522v2-abstract-full" style="display: none;"> TensorFlow-GNN (TF-GNN) is a scalable library for Graph Neural Networks in TensorFlow. It is designed from the bottom up to support the kinds of rich heterogeneous graph data that occurs in today's information ecosystems. In addition to enabling machine learning researchers and advanced developers, TF-GNN offers low-code solutions to empower the broader developer community in graph learning. Many production models at Google use TF-GNN, and it has been recently released as an open source project. In this paper we describe the TF-GNN data model, its Keras message passing API, and relevant capabilities such as graph sampling and distributed training. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.03522v2-abstract-full').style.display = 'none'; document.getElementById('2207.03522v2-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 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 7 July, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2205.10293">arXiv:2205.10293</a> <span> [<a href="https://arxiv.org/pdf/2205.10293">pdf</a>, <a href="https://arxiv.org/format/2205.10293">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="Social and Information Networks">cs.SI</span> </div> </div> <p class="title is-5 mathjax"> DELATOR: Money Laundering Detection via Multi-Task Learning on Large Transaction Graphs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Assump%C3%A7%C3%A3o%2C+H+S">Henrique S. Assump莽茫o</a>, <a href="/search/cs?searchtype=author&query=Souza%2C+F">Fabr铆cio Souza</a>, <a href="/search/cs?searchtype=author&query=Campos%2C+L+L">Leandro Lacerda Campos</a>, <a href="/search/cs?searchtype=author&query=Pires%2C+V+T+d+C">Vin铆cius T. de Castro Pires</a>, <a href="/search/cs?searchtype=author&query=de+Almeida%2C+P+M+L">Paulo M. Laurentys de Almeida</a>, <a href="/search/cs?searchtype=author&query=Murai%2C+F">Fabricio Murai</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="2205.10293v2-abstract-short" style="display: inline;"> Money laundering has become one of the most relevant criminal activities in modern societies, as it causes massive financial losses for governments, banks and other institutions. Detecting such activities is among the top priorities when it comes to financial analysis, but current approaches are often costly and labor intensive partly due to the sheer amount of data to be analyzed. Hence, there is… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.10293v2-abstract-full').style.display = 'inline'; document.getElementById('2205.10293v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2205.10293v2-abstract-full" style="display: none;"> Money laundering has become one of the most relevant criminal activities in modern societies, as it causes massive financial losses for governments, banks and other institutions. Detecting such activities is among the top priorities when it comes to financial analysis, but current approaches are often costly and labor intensive partly due to the sheer amount of data to be analyzed. Hence, there is a growing need for automatic anti-money laundering systems to assist experts. In this work, we propose DELATOR, a novel framework for detecting money laundering activities based on graph neural networks that learn from large-scale temporal graphs. DELATOR provides an effective and efficient method for learning from heavily imbalanced graph data, by adapting concepts from the GraphSMOTE framework and incorporating elements of multi-task learning to obtain rich node embeddings for node classification. DELATOR outperforms all considered baselines, including an off-the-shelf solution from Amazon AWS by 23% with respect to AUC-ROC. We also conducted real experiments that led to the discovery of 7 new suspicious cases among the 50 analyzed ones, which have been reported to the authorities. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.10293v2-abstract-full').style.display = 'none'; document.getElementById('2205.10293v2-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 October, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 May, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2022. </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 in the 2022 IEEE International Conference on Big Data (IEEE BigData) as a short paper</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2111.06161">arXiv:2111.06161</a> <span> [<a href="https://arxiv.org/pdf/2111.06161">pdf</a>, <a href="https://arxiv.org/format/2111.06161">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> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> </div> </div> <p class="title is-5 mathjax"> Understanding mobility in networks: A node embedding approach </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Barros%2C+M+F+C">Matheus F. C. Barros</a>, <a href="/search/cs?searchtype=author&query=Ferreira%2C+C+H+G">Carlos H. G. Ferreira</a>, <a href="/search/cs?searchtype=author&query=Santos%2C+B+P+d">Bruno Pereira dos Santos</a>, <a href="/search/cs?searchtype=author&query=J%C3%BAnior%2C+L+A+P">Louren莽o A. P. J煤nior</a>, <a href="/search/cs?searchtype=author&query=Mellia%2C+M">Marco Mellia</a>, <a href="/search/cs?searchtype=author&query=Almeida%2C+J+M">Jussara M. Almeida</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="2111.06161v1-abstract-short" style="display: inline;"> Motivated by the growing number of mobile devices capable of connecting and exchanging messages, we propose a methodology aiming to model and analyze node mobility in networks. We note that many existing solutions in the literature rely on topological measurements calculated directly on the graph of node contacts, aiming to capture the notion of the node's importance in terms of connectivity and m… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.06161v1-abstract-full').style.display = 'inline'; document.getElementById('2111.06161v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2111.06161v1-abstract-full" style="display: none;"> Motivated by the growing number of mobile devices capable of connecting and exchanging messages, we propose a methodology aiming to model and analyze node mobility in networks. We note that many existing solutions in the literature rely on topological measurements calculated directly on the graph of node contacts, aiming to capture the notion of the node's importance in terms of connectivity and mobility patterns beneficial for prototyping, design, and deployment of mobile networks. However, each measure has its specificity and fails to generalize the node importance notions that ultimately change over time. Unlike previous approaches, our methodology is based on a node embedding method that models and unveils the nodes' importance in mobility and connectivity patterns while preserving their spatial and temporal characteristics. We focus on a case study based on a trace of group meetings. The results show that our methodology provides a rich representation for extracting different mobility and connectivity patterns, which can be helpful for various applications and services in mobile networks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.06161v1-abstract-full').style.display = 'none'; document.getElementById('2111.06161v1-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 November, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2109.13963">arXiv:2109.13963</a> <span> [<a href="https://arxiv.org/pdf/2109.13963">pdf</a>, <a href="https://arxiv.org/format/2109.13963">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="Performance">cs.PF</span> </div> </div> <p class="title is-5 mathjax"> Smart at what cost? Characterising Mobile Deep Neural Networks in the wild </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Almeida%2C+M">Mario Almeida</a>, <a href="/search/cs?searchtype=author&query=Laskaridis%2C+S">Stefanos Laskaridis</a>, <a href="/search/cs?searchtype=author&query=Mehrotra%2C+A">Abhinav Mehrotra</a>, <a href="/search/cs?searchtype=author&query=Dudziak%2C+L">Lukasz Dudziak</a>, <a href="/search/cs?searchtype=author&query=Leontiadis%2C+I">Ilias Leontiadis</a>, <a href="/search/cs?searchtype=author&query=Lane%2C+N+D">Nicholas D. Lane</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="2109.13963v1-abstract-short" style="display: inline;"> With smartphones' omnipresence in people's pockets, Machine Learning (ML) on mobile is gaining traction as devices become more powerful. With applications ranging from visual filters to voice assistants, intelligence on mobile comes in many forms and facets. However, Deep Neural Network (DNN) inference remains a compute intensive workload, with devices struggling to support intelligence at the cos… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.13963v1-abstract-full').style.display = 'inline'; document.getElementById('2109.13963v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2109.13963v1-abstract-full" style="display: none;"> With smartphones' omnipresence in people's pockets, Machine Learning (ML) on mobile is gaining traction as devices become more powerful. With applications ranging from visual filters to voice assistants, intelligence on mobile comes in many forms and facets. However, Deep Neural Network (DNN) inference remains a compute intensive workload, with devices struggling to support intelligence at the cost of responsiveness.On the one hand, there is significant research on reducing model runtime requirements and supporting deployment on embedded devices. On the other hand, the strive to maximise the accuracy of a task is supported by deeper and wider neural networks, making mobile deployment of state-of-the-art DNNs a moving target. In this paper, we perform the first holistic study of DNN usage in the wild in an attempt to track deployed models and match how these run on widely deployed devices. To this end, we analyse over 16k of the most popular apps in the Google Play Store to characterise their DNN usage and performance across devices of different capabilities, both across tiers and generations. Simultaneously, we measure the models' energy footprint, as a core cost dimension of any mobile deployment. To streamline the process, we have developed gaugeNN, a tool that automates the deployment, measurement and analysis of DNNs on devices, with support for different frameworks and platforms. Results from our experience study paint the landscape of deep learning deployments on smartphones and indicate their popularity across app developers. Furthermore, our study shows the gap between bespoke techniques and real-world deployments and the need for optimised deployment of deep learning models in a highly dynamic and heterogeneous ecosystem. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.13963v1-abstract-full').style.display = 'none'; document.getElementById('2109.13963v1-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 September, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2021. </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 the ACM Internet Measurement Conference (IMC), 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/2109.10462">arXiv:2109.10462</a> <span> [<a href="https://arxiv.org/pdf/2109.10462">pdf</a>, <a href="https://arxiv.org/format/2109.10462">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</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="Computers and Society">cs.CY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation">stat.CO</span> </div> </div> <p class="title is-5 mathjax"> A Hierarchical Network-Oriented Analysis of User Participation in Misinformation Spread on WhatsApp </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nobre%2C+G+P">Gabriel Peres Nobre</a>, <a href="/search/cs?searchtype=author&query=Ferreira%2C+C+H+G">Carlos H. G. Ferreira</a>, <a href="/search/cs?searchtype=author&query=Almeida%2C+J+M">Jussara M. Almeida</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="2109.10462v1-abstract-short" style="display: inline;"> WhatsApp emerged as a major communication platform in many countries in the recent years. Despite offering only one-to-one and small group conversations, WhatsApp has been shown to enable the formation of a rich underlying network, crossing the boundaries of existing groups, and with structural properties that favor information dissemination at large. Indeed, WhatsApp has reportedly been used as a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.10462v1-abstract-full').style.display = 'inline'; document.getElementById('2109.10462v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2109.10462v1-abstract-full" style="display: none;"> WhatsApp emerged as a major communication platform in many countries in the recent years. Despite offering only one-to-one and small group conversations, WhatsApp has been shown to enable the formation of a rich underlying network, crossing the boundaries of existing groups, and with structural properties that favor information dissemination at large. Indeed, WhatsApp has reportedly been used as a forum of misinformation campaigns with significant social, political and economic consequences in several countries. In this article, we aim at complementing recent studies on misinformation spread on WhatsApp, mostly focused on content properties and propagation dynamics, by looking into the network that connects users sharing the same piece of content. Specifically, we present a hierarchical network-oriented characterization of the users engaged in misinformation spread by focusing on three perspectives: individuals, WhatsApp groups and user communities, i.e., groupings of users who, intentionally or not, share the same content disproportionately often. By analyzing sharing and network topological properties, our study offers valuable insights into how WhatsApp users leverage the underlying network connecting different groups to gain large reach in the spread of misinformation on the platform. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.10462v1-abstract-full').style.display = 'none'; document.getElementById('2109.10462v1-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 September, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2021. </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">Paper Accepted in Information Processing & Management, Elsevier</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2109.09152">arXiv:2109.09152</a> <span> [<a href="https://arxiv.org/pdf/2109.09152">pdf</a>, <a href="https://arxiv.org/format/2109.09152">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</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.osnem.2021.100155.">10.1016/j.osnem.2021.100155. <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> On the Dynamics of Political Discussions on Instagram: A Network Perspective </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ferreira%2C+C+H+G">Carlos H. G. Ferreira</a>, <a href="/search/cs?searchtype=author&query=Murai%2C+F">Fabricio Murai</a>, <a href="/search/cs?searchtype=author&query=Silva%2C+A+P+C">Ana P. C. Silva</a>, <a href="/search/cs?searchtype=author&query=Almeida%2C+J+M">Jussara M. Almeida</a>, <a href="/search/cs?searchtype=author&query=Trevisan%2C+M">Martino Trevisan</a>, <a href="/search/cs?searchtype=author&query=Vassio%2C+L">Luca Vassio</a>, <a href="/search/cs?searchtype=author&query=Mellia%2C+M">Marco Mellia</a>, <a href="/search/cs?searchtype=author&query=Drago%2C+I">Idilio Drago</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="2109.09152v3-abstract-short" style="display: inline;"> Instagram has been increasingly used as a source of information especially among the youth. As a result, political figures now leverage the platform to spread opinions and political agenda. We here analyze online discussions on Instagram, notably in political topics, from a network perspective. Specifically, we investigate the emergence of communities of co-commenters, that is, groups of users who… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.09152v3-abstract-full').style.display = 'inline'; document.getElementById('2109.09152v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2109.09152v3-abstract-full" style="display: none;"> Instagram has been increasingly used as a source of information especially among the youth. As a result, political figures now leverage the platform to spread opinions and political agenda. We here analyze online discussions on Instagram, notably in political topics, from a network perspective. Specifically, we investigate the emergence of communities of co-commenters, that is, groups of users who often interact by commenting on the same posts and may be driving the ongoing online discussions. In particular, we are interested in salient co-interactions, i.e., interactions of co-commenters that occur more often than expected by chance and under independent behavior. Unlike casual and accidental co-interactions which normally happen in large volumes, salient co-interactions are key elements driving the online discussions and, ultimately, the information dissemination. We base our study on the analysis of 10 weeks of data centered around major elections in Brazil and Italy, following both politicians and other celebrities. We extract and characterize the communities of co-commenters in terms of topological structure, properties of the discussions carried out by community members, and how some community properties, notably community membership and topics, evolve over time. We show that communities discussing political topics tend to be more engaged in the debate by writing longer comments, using more emojis, hashtags and negative words than in other subjects. Also, communities built around political discussions tend to be more dynamic, although top commenters remain active and preserve community membership over time. Moreover, we observe a great diversity in discussed topics over time: whereas some topics attract attention only momentarily, others, centered around more fundamental political discussions, remain consistently active over time. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.09152v3-abstract-full').style.display = 'none'; document.getElementById('2109.09152v3-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 September, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 19 September, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Online Social Networks and Media, Volume 25, 2021, ISSN 2468-6964 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2108.12214">arXiv:2108.12214</a> <span> [<a href="https://arxiv.org/pdf/2108.12214">pdf</a>, <a href="https://arxiv.org/format/2108.12214">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link 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="Performance">cs.PF</span> </div> </div> <p class="title is-5 mathjax"> Machine Learning for Performance Prediction of Spark Cloud Applications </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Maros%2C+A">Alexandre Maros</a>, <a href="/search/cs?searchtype=author&query=Murai%2C+F">Fabricio Murai</a>, <a href="/search/cs?searchtype=author&query=da+Silva%2C+A+P+C">Ana Paula Couto da Silva</a>, <a href="/search/cs?searchtype=author&query=Almeida%2C+J+M">Jussara M. Almeida</a>, <a href="/search/cs?searchtype=author&query=Lattuada%2C+M">Marco Lattuada</a>, <a href="/search/cs?searchtype=author&query=Gianniti%2C+E">Eugenio Gianniti</a>, <a href="/search/cs?searchtype=author&query=Hosseini%2C+M">Marjan Hosseini</a>, <a href="/search/cs?searchtype=author&query=Ardagna%2C+D">Danilo Ardagna</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="2108.12214v1-abstract-short" style="display: inline;"> Big data applications and analytics are employed in many sectors for a variety of goals: improving customers satisfaction, predicting market behavior or improving processes in public health. These applications consist of complex software stacks that are often run on cloud systems. Predicting execution times is important for estimating the cost of cloud services and for effectively managing the und… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2108.12214v1-abstract-full').style.display = 'inline'; document.getElementById('2108.12214v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2108.12214v1-abstract-full" style="display: none;"> Big data applications and analytics are employed in many sectors for a variety of goals: improving customers satisfaction, predicting market behavior or improving processes in public health. These applications consist of complex software stacks that are often run on cloud systems. Predicting execution times is important for estimating the cost of cloud services and for effectively managing the underlying resources at runtime. Machine Learning (ML), providing black box solutions to model the relationship between application performance and system configuration without requiring in-detail knowledge of the system, has become a popular way of predicting the performance of big data applications. We investigate the cost-benefits of using supervised ML models for predicting the performance of applications on Spark, one of today's most widely used frameworks for big data analysis. We compare our approach with \textit{Ernest} (an ML-based technique proposed in the literature by the Spark inventors) on a range of scenarios, application workloads, and cloud system configurations. Our experiments show that Ernest can accurately estimate the performance of very regular applications, but it fails when applications exhibit more irregular patterns and/or when extrapolating on bigger data set sizes. Results show that our models match or exceed Ernest's performance, sometimes enabling us to reduce the prediction error from 126-187% to only 5-19%. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2108.12214v1-abstract-full').style.display = 'none'; document.getElementById('2108.12214v1-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 August, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2021. </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 2019 IEEE 12th International Conference on Cloud Computing (CLOUD)</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> B.8.2; I.2 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2107.04702">arXiv:2107.04702</a> <span> [<a href="https://arxiv.org/pdf/2107.04702">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Neural and Evolutionary Computing">cs.NE</span> </div> </div> <p class="title is-5 mathjax"> Um Metodo para Busca Automatica de Redes Neurais Artificiais </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=da+Silva%2C+A+P">Anderson P. da Silva</a>, <a href="/search/cs?searchtype=author&query=Ludermir%2C+T+B">Teresa B. Ludermir</a>, <a href="/search/cs?searchtype=author&query=Almeida%2C+L+M">Leandro M. Almeida</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="2107.04702v1-abstract-short" style="display: inline;"> This paper describes a method that automatically searches Artificial Neural Networks using Cellular Genetic Algorithms. The main difference of this method for a common genetic algorithm is the use of a cellular automaton capable of providing the location for individuals, reducing the possibility of local minima in search space. This method employs an evolutionary search for simultaneous choices of… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2107.04702v1-abstract-full').style.display = 'inline'; document.getElementById('2107.04702v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2107.04702v1-abstract-full" style="display: none;"> This paper describes a method that automatically searches Artificial Neural Networks using Cellular Genetic Algorithms. The main difference of this method for a common genetic algorithm is the use of a cellular automaton capable of providing the location for individuals, reducing the possibility of local minima in search space. This method employs an evolutionary search for simultaneous choices of initial weights, transfer functions, architectures and learning rules. Experimental results have shown that the developed method can find compact, efficient networks with a satisfactory generalization power and with shorter training times when compared to other methods found in the literature. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2107.04702v1-abstract-full').style.display = 'none'; document.getElementById('2107.04702v1-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 July, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2021. </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, in Portuguese, 4 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/2106.04805">arXiv:2106.04805</a> <span> [<a href="https://arxiv.org/pdf/2106.04805">pdf</a>, <a href="https://arxiv.org/format/2106.04805">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">stat.ML</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Probability">math.PR</span> </div> </div> <p class="title is-5 mathjax"> Streaming Belief Propagation for Community Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yuchen Wu</a>, <a href="/search/cs?searchtype=author&query=Bateni%2C+M">MohammadHossein Bateni</a>, <a href="/search/cs?searchtype=author&query=Linhares%2C+A">Andre Linhares</a>, <a href="/search/cs?searchtype=author&query=de+Almeida%2C+F+M+G">Filipe Miguel Goncalves de Almeida</a>, <a href="/search/cs?searchtype=author&query=Montanari%2C+A">Andrea Montanari</a>, <a href="/search/cs?searchtype=author&query=Norouzi-Fard%2C+A">Ashkan Norouzi-Fard</a>, <a href="/search/cs?searchtype=author&query=Tardos%2C+J">Jakab Tardos</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="2106.04805v2-abstract-short" style="display: inline;"> The community detection problem requires to cluster the nodes of a network into a small number of well-connected "communities". There has been substantial recent progress in characterizing the fundamental statistical limits of community detection under simple stochastic block models. However, in real-world applications, the network structure is typically dynamic, with nodes that join over time. In… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.04805v2-abstract-full').style.display = 'inline'; document.getElementById('2106.04805v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2106.04805v2-abstract-full" style="display: none;"> The community detection problem requires to cluster the nodes of a network into a small number of well-connected "communities". There has been substantial recent progress in characterizing the fundamental statistical limits of community detection under simple stochastic block models. However, in real-world applications, the network structure is typically dynamic, with nodes that join over time. In this setting, we would like a detection algorithm to perform only a limited number of updates at each node arrival. While standard voting approaches satisfy this constraint, it is unclear whether they exploit the network information optimally. We introduce a simple model for networks growing over time which we refer to as streaming stochastic block model (StSBM). Within this model, we prove that voting algorithms have fundamental limitations. We also develop a streaming belief-propagation (StreamBP) approach, for which we prove optimality in certain regimes. We validate our theoretical findings on synthetic and real data. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.04805v2-abstract-full').style.display = 'none'; document.getElementById('2106.04805v2-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 June, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 June, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2021. </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, 13 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/2106.00799">arXiv:2106.00799</a> <span> [<a href="https://arxiv.org/pdf/2106.00799">pdf</a>, <a href="https://arxiv.org/format/2106.00799">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 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.isprsjprs.2021.07.001">10.1016/j.isprsjprs.2021.07.001 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Multi-task fully convolutional network for tree species mapping in dense forests using small training hyperspectral data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=La+Rosa%2C+L+E+C">Laura Elena Cu茅 La Rosa</a>, <a href="/search/cs?searchtype=author&query=Sothe%2C+C">Camile Sothe</a>, <a href="/search/cs?searchtype=author&query=Feitosa%2C+R+Q">Raul Queiroz Feitosa</a>, <a href="/search/cs?searchtype=author&query=de+Almeida%2C+C+M">Cl谩udia Maria de Almeida</a>, <a href="/search/cs?searchtype=author&query=Schimalski%2C+M+B">Marcos Benedito Schimalski</a>, <a href="/search/cs?searchtype=author&query=Oliveira%2C+D+A+B">Dario Augusto Borges Oliveira</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="2106.00799v2-abstract-short" style="display: inline;"> This work proposes a multi-task fully convolutional architecture for tree species mapping in dense forests from sparse and scarce polygon-level annotations using hyperspectral UAV-borne data. Our model implements a partial loss function that enables dense tree semantic labeling outcomes from non-dense training samples, and a distance regression complementary task that enforces tree crown boundary… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.00799v2-abstract-full').style.display = 'inline'; document.getElementById('2106.00799v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2106.00799v2-abstract-full" style="display: none;"> This work proposes a multi-task fully convolutional architecture for tree species mapping in dense forests from sparse and scarce polygon-level annotations using hyperspectral UAV-borne data. Our model implements a partial loss function that enables dense tree semantic labeling outcomes from non-dense training samples, and a distance regression complementary task that enforces tree crown boundary constraints and substantially improves the model performance. Our multi-task architecture uses a shared backbone network that learns common representations for both tasks and two task-specific decoders, one for the semantic segmentation output and one for the distance map regression. We report that introducing the complementary task boosts the semantic segmentation performance compared to the single-task counterpart in up to 11% reaching an average user's accuracy of 88.63% and an average producer's accuracy of 88.59%, achieving state-of-art performance for tree species classification in tropical forests. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.00799v2-abstract-full').style.display = 'none'; document.getElementById('2106.00799v2-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 September, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 1 June, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2021. </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">Full version of preprint accepted at ISPRS Journal of Photogrammetry and Remote Sensing</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2104.09949">arXiv:2104.09949</a> <span> [<a href="https://arxiv.org/pdf/2104.09949">pdf</a>, <a href="https://arxiv.org/format/2104.09949">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link 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="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/10.1145/3510831">10.1145/3510831 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> DynO: Dynamic Onloading of Deep Neural Networks from Cloud to Device </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Almeida%2C+M">Mario Almeida</a>, <a href="/search/cs?searchtype=author&query=Laskaridis%2C+S">Stefanos Laskaridis</a>, <a href="/search/cs?searchtype=author&query=Venieris%2C+S+I">Stylianos I. Venieris</a>, <a href="/search/cs?searchtype=author&query=Leontiadis%2C+I">Ilias Leontiadis</a>, <a href="/search/cs?searchtype=author&query=Lane%2C+N+D">Nicholas D. Lane</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="2104.09949v2-abstract-short" style="display: inline;"> Recently, there has been an explosive growth of mobile and embedded applications using convolutional neural networks(CNNs). To alleviate their excessive computational demands, developers have traditionally resorted to cloud offloading, inducing high infrastructure costs and a strong dependence on networking conditions. On the other end, the emergence of powerful SoCs is gradually enabling on-devic… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2104.09949v2-abstract-full').style.display = 'inline'; document.getElementById('2104.09949v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2104.09949v2-abstract-full" style="display: none;"> Recently, there has been an explosive growth of mobile and embedded applications using convolutional neural networks(CNNs). To alleviate their excessive computational demands, developers have traditionally resorted to cloud offloading, inducing high infrastructure costs and a strong dependence on networking conditions. On the other end, the emergence of powerful SoCs is gradually enabling on-device execution. Nonetheless, low- and mid-tier platforms still struggle to run state-of-the-art CNNs sufficiently. In this paper, we present DynO, a distributed inference framework that combines the best of both worlds to address several challenges, such as device heterogeneity, varying bandwidth and multi-objective requirements. Key components that enable this are its novel CNN-specific data packing method, which exploits the variability of precision needs in different parts of the CNN when onloading computation, and its novel scheduler that jointly tunes the partition point and transferred data precision at run time to adapt inference to its execution environment. Quantitative evaluation shows that DynO outperforms the current state-of-the-art, improving throughput by over an order of magnitude over device-only execution and up to 7.9x over competing CNN offloading systems, with up to 60x less data transferred. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2104.09949v2-abstract-full').style.display = 'none'; document.getElementById('2104.09949v2-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 January, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 April, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2021. </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 the ACM Transactions on Embedded Computing Systems (TECS) in the special issue on Accelerating AI on the Edge</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2103.00535">arXiv:2103.00535</a> <span> [<a href="https://arxiv.org/pdf/2103.00535">pdf</a>, <a href="https://arxiv.org/format/2103.00535">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> </div> </div> <p class="title is-5 mathjax"> A multi-objective time series analysis of community mobility reduction comparing first and second COVID-19 waves </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=da+Silva%2C+G+C">Gabriela Cavalcante da Silva</a>, <a href="/search/cs?searchtype=author&query=de+Almeida%2C+F+M">Fernanda Monteiro de Almeida</a>, <a href="/search/cs?searchtype=author&query=Oliveira%2C+S">Sabrina Oliveira</a>, <a href="/search/cs?searchtype=author&query=Bezerra%2C+L+C+T">Leonardo C. T. Bezerra</a>, <a href="/search/cs?searchtype=author&query=Wanner%2C+E+F">Elizabeth F. Wanner</a>, <a href="/search/cs?searchtype=author&query=Takahashi%2C+R+H+C">Ricardo H. C. Takahashi</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="2103.00535v1-abstract-short" style="display: inline;"> With the logistic challenges faced by most countries for the production, distribution, and application of vaccines for the novel coronavirus disease~(COVID-19), social distancing~(SD) remains the most tangible approach to mitigate the spread of the virus. To assist SD monitoring, several tech companies have made publicly available anonymized mobility data. In this work, we conduct a multi-objectiv… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2103.00535v1-abstract-full').style.display = 'inline'; document.getElementById('2103.00535v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2103.00535v1-abstract-full" style="display: none;"> With the logistic challenges faced by most countries for the production, distribution, and application of vaccines for the novel coronavirus disease~(COVID-19), social distancing~(SD) remains the most tangible approach to mitigate the spread of the virus. To assist SD monitoring, several tech companies have made publicly available anonymized mobility data. In this work, we conduct a multi-objective mobility reduction rate comparison between the first and second COVID-19 waves in several localities from America and Europe using Google community mobility reports~(CMR) data. Through multi-dimensional visualization, we are able to compare in a Pareto-compliant way the reduction in mobility from the different lockdown periods for each locality selected, simultaneously considering all place categories provided in CMR. In addition, our analysis comprises a 56-day lockdown period for each locality and COVID-19 wave, which we analyze both as 56-day periods and as 14-day consecutive windows. Results vary considerably as a function of the locality considered, particularly when the temporal evolution of the mobility reduction is considered. We thus discuss each locality individually, relating social distancing measures and the reduction observed. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2103.00535v1-abstract-full').style.display = 'none'; document.getElementById('2103.00535v1-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 February, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2102.13451">arXiv:2102.13451</a> <span> [<a href="https://arxiv.org/pdf/2102.13451">pdf</a>, <a href="https://arxiv.org/format/2102.13451">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> <p class="title is-5 mathjax"> FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Horvath%2C+S">Samuel Horvath</a>, <a href="/search/cs?searchtype=author&query=Laskaridis%2C+S">Stefanos Laskaridis</a>, <a href="/search/cs?searchtype=author&query=Almeida%2C+M">Mario Almeida</a>, <a href="/search/cs?searchtype=author&query=Leontiadis%2C+I">Ilias Leontiadis</a>, <a href="/search/cs?searchtype=author&query=Venieris%2C+S+I">Stylianos I. Venieris</a>, <a href="/search/cs?searchtype=author&query=Lane%2C+N+D">Nicholas D. Lane</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="2102.13451v5-abstract-short" style="display: inline;"> Federated Learning (FL) has been gaining significant traction across different ML tasks, ranging from vision to keyboard predictions. In large-scale deployments, client heterogeneity is a fact and constitutes a primary problem for fairness, training performance and accuracy. Although significant efforts have been made into tackling statistical data heterogeneity, the diversity in the processing ca… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2102.13451v5-abstract-full').style.display = 'inline'; document.getElementById('2102.13451v5-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2102.13451v5-abstract-full" style="display: none;"> Federated Learning (FL) has been gaining significant traction across different ML tasks, ranging from vision to keyboard predictions. In large-scale deployments, client heterogeneity is a fact and constitutes a primary problem for fairness, training performance and accuracy. Although significant efforts have been made into tackling statistical data heterogeneity, the diversity in the processing capabilities and network bandwidth of clients, termed as system heterogeneity, has remained largely unexplored. Current solutions either disregard a large portion of available devices or set a uniform limit on the model's capacity, restricted by the least capable participants. In this work, we introduce Ordered Dropout, a mechanism that achieves an ordered, nested representation of knowledge in deep neural networks (DNNs) and enables the extraction of lower footprint submodels without the need of retraining. We further show that for linear maps our Ordered Dropout is equivalent to SVD. We employ this technique, along with a self-distillation methodology, in the realm of FL in a framework called FjORD. FjORD alleviates the problem of client system heterogeneity by tailoring the model width to the client's capabilities. Extensive evaluation on both CNNs and RNNs across diverse modalities shows that FjORD consistently leads to significant performance gains over state-of-the-art baselines, while maintaining its nested structure. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2102.13451v5-abstract-full').style.display = 'none'; document.getElementById('2102.13451v5-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 January, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 26 February, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2021. </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 the 35th Conference on Neural Information Processing Systems (NeurIPS), 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/2102.13192">arXiv:2102.13192</a> <span> [<a href="https://arxiv.org/pdf/2102.13192">pdf</a>, <a href="https://arxiv.org/format/2102.13192">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"> PlaceRAN: Optimal Placement of Virtualized Network Functions in the Next-generation Radio Access Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Morais%2C+F+Z">Fernando Zanferrari Morais</a>, <a href="/search/cs?searchtype=author&query=de+Almeida%2C+G+M">Gabriel Matheus de Almeida</a>, <a href="/search/cs?searchtype=author&query=Pinto%2C+L">Leizer Pinto</a>, <a href="/search/cs?searchtype=author&query=Cardoso%2C+K+V">Kleber Vieira Cardoso</a>, <a href="/search/cs?searchtype=author&query=Contreras%2C+L+M">Luis M. Contreras</a>, <a href="/search/cs?searchtype=author&query=Righi%2C+R+d+R">Rodrigo da Rosa Righi</a>, <a href="/search/cs?searchtype=author&query=Both%2C+C+B">Cristiano Bonato Both</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="2102.13192v4-abstract-short" style="display: inline;"> The fifth-generation mobile evolution enables several transformations on Next Generation Radio Access Networks (NG-RAN). The RAN protocol stack is splitting into eight possible disaggregated options combined into three network units, i.e., Central, Distributed, and Radio. Besides that, further advances allow the RAN software to be virtualized on top of general-purpose vendor-neutral hardware, deal… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2102.13192v4-abstract-full').style.display = 'inline'; document.getElementById('2102.13192v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2102.13192v4-abstract-full" style="display: none;"> The fifth-generation mobile evolution enables several transformations on Next Generation Radio Access Networks (NG-RAN). The RAN protocol stack is splitting into eight possible disaggregated options combined into three network units, i.e., Central, Distributed, and Radio. Besides that, further advances allow the RAN software to be virtualized on top of general-purpose vendor-neutral hardware, dealing with the concept of virtualized RAN (vRAN). The disaggregated network units initiatives reach full interoperability based on the Open RAN (O-RAN). The combination of NG-RAN and vRAN results in vNG-RAN, enabling the management of disaggregated units and protocols as a set of radio functions. The placement of these functions is challenging since the best decision can be based on multiple constraints, such as the RAN protocol stack split, routing paths of transport networks with restricted bandwidth and latency requirements, different topologies and link capabilities, asymmetric computational resources, etc. This article proposes the first exact model for the placement optimization of radio functions for vNG-RAN planning, named PlaceRAN. The main objective is to minimize the computing resources and maximize the aggregation of radio functions. The PlaceRAN evaluation considered two realistic network topologies. Our results reveal that the PlaceRAN model achieves an optimized high-performance aggregation level, it is flexible for RAN deployment overcoming the network restrictions, and it is up to date with the most advanced vNG-RAN design and development. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2102.13192v4-abstract-full').style.display = 'none'; document.getElementById('2102.13192v4-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 March, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 25 February, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2102.00461">arXiv:2102.00461</a> <span> [<a href="https://arxiv.org/pdf/2102.00461">pdf</a>, <a href="https://arxiv.org/format/2102.00461">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="Applications">stat.AP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Multilingual Email Zoning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jardim%2C+B">Bruno Jardim</a>, <a href="/search/cs?searchtype=author&query=Rei%2C+R">Ricardo Rei</a>, <a href="/search/cs?searchtype=author&query=Almeida%2C+M+S+C">Mariana S. C. Almeida</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="2102.00461v2-abstract-short" style="display: inline;"> The segmentation of emails into functional zones (also dubbed email zoning) is a relevant preprocessing step for most NLP tasks that deal with emails. However, despite the multilingual character of emails and their applications, previous literature regarding email zoning corpora and systems was developed essentially for English. In this paper, we analyse the existing email zoning corpora and pro… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2102.00461v2-abstract-full').style.display = 'inline'; document.getElementById('2102.00461v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2102.00461v2-abstract-full" style="display: none;"> The segmentation of emails into functional zones (also dubbed email zoning) is a relevant preprocessing step for most NLP tasks that deal with emails. However, despite the multilingual character of emails and their applications, previous literature regarding email zoning corpora and systems was developed essentially for English. In this paper, we analyse the existing email zoning corpora and propose a new multilingual benchmark composed of 625 emails in Portuguese, Spanish and French. Moreover, we introduce OKAPI, the first multilingual email segmentation model based on a language agnostic sentence encoder. Besides generalizing well for unseen languages, our model is competitive with current English benchmarks, and reached new state-of-the-art performances for domain adaptation tasks in English. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2102.00461v2-abstract-full').style.display = 'none'; document.getElementById('2102.00461v2-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, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 31 January, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2021. </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 EACL 2021 SRW (https://sites.google.com/view/eaclsrw2021/home); 6 pages with 2 Figures and 8 Tables, plus references; Cleverly Multilingual Zoning Corpus available at https://github.com/cleverly-ai/multilingual-email-zoning</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2011.09012">arXiv:2011.09012</a> <span> [<a href="https://arxiv.org/pdf/2011.09012">pdf</a>, <a href="https://arxiv.org/format/2011.09012">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Programming Languages">cs.PL</span> </div> </div> <p class="title is-5 mathjax"> RustViz: Interactively Visualizing Ownership and Borrowing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gongming"> Gongming</a>, <a href="/search/cs?searchtype=author&query=Luo"> Luo</a>, <a href="/search/cs?searchtype=author&query=Reddy%2C+V">Vishnu Reddy</a>, <a href="/search/cs?searchtype=author&query=Almeida%2C+M">Marcelo Almeida</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Y">Yingying Zhu</a>, <a href="/search/cs?searchtype=author&query=Du%2C+K">Ke Du</a>, <a href="/search/cs?searchtype=author&query=Omar%2C+C">Cyrus Omar</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="2011.09012v1-abstract-short" style="display: inline;"> Rust is a systems programming language that guarantees memory safety without the need for a garbage collector by statically tracking ownership and borrowing events. The associated rules are subtle and unique among industry programming languages, which can make learning Rust more challenging. Motivated by the challenges that Rust learners face, we are developing RustViz, a tool that allows teachers… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2011.09012v1-abstract-full').style.display = 'inline'; document.getElementById('2011.09012v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2011.09012v1-abstract-full" style="display: none;"> Rust is a systems programming language that guarantees memory safety without the need for a garbage collector by statically tracking ownership and borrowing events. The associated rules are subtle and unique among industry programming languages, which can make learning Rust more challenging. Motivated by the challenges that Rust learners face, we are developing RustViz, a tool that allows teachers to generate an interactive timeline depicting ownership and borrowing events for each variable in a Rust code example. These visualizations are intended to help Rust learners develop an understanding of ownership and borrowing by example. This paper introduces RustViz by example, shows how teachers can use it to generate visualizations, describes learning goals, and proposes a study designed to evaluate RustViz based on these learning goals. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2011.09012v1-abstract-full').style.display = 'none'; document.getElementById('2011.09012v1-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 November, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2020. </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">9 pages, 3 figures. Presented at HATRA 2020 (Human Aspects of Types and Reasoning Assistants)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2010.06992">arXiv:2010.06992</a> <span> [<a href="https://arxiv.org/pdf/2010.06992">pdf</a>, <a href="https://arxiv.org/format/2010.06992">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="Social and Information Networks">cs.SI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> InstantEmbedding: Efficient Local Node Representations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Post%C4%83varu%2C+%C5%9E">艦tefan Post膬varu</a>, <a href="/search/cs?searchtype=author&query=Tsitsulin%2C+A">Anton Tsitsulin</a>, <a href="/search/cs?searchtype=author&query=de+Almeida%2C+F+M+G">Filipe Miguel Gon莽alves de Almeida</a>, <a href="/search/cs?searchtype=author&query=Tian%2C+Y">Yingtao Tian</a>, <a href="/search/cs?searchtype=author&query=Lattanzi%2C+S">Silvio Lattanzi</a>, <a href="/search/cs?searchtype=author&query=Perozzi%2C+B">Bryan Perozzi</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="2010.06992v1-abstract-short" style="display: inline;"> In this paper, we introduce InstantEmbedding, an efficient method for generating single-node representations using local PageRank computations. We theoretically prove that our approach produces globally consistent representations in sublinear time. We demonstrate this empirically by conducting extensive experiments on real-world datasets with over a billion edges. Our experiments confirm that Inst… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2010.06992v1-abstract-full').style.display = 'inline'; document.getElementById('2010.06992v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2010.06992v1-abstract-full" style="display: none;"> In this paper, we introduce InstantEmbedding, an efficient method for generating single-node representations using local PageRank computations. We theoretically prove that our approach produces globally consistent representations in sublinear time. We demonstrate this empirically by conducting extensive experiments on real-world datasets with over a billion edges. Our experiments confirm that InstantEmbedding requires drastically less computation time (over 9,000 times faster) and less memory (by over 8,000 times) to produce a single node's embedding than traditional methods including DeepWalk, node2vec, VERSE, and FastRP. We also show that our method produces high quality representations, demonstrating results that meet or exceed the state of the art for unsupervised representation learning on tasks like node classification and link prediction. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2010.06992v1-abstract-full').style.display = 'none'; document.getElementById('2010.06992v1-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 October, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2020. </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, 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/2009.11751">arXiv:2009.11751</a> <span> [<a href="https://arxiv.org/pdf/2009.11751">pdf</a>, <a href="https://arxiv.org/ps/2009.11751">ps</a>, <a href="https://arxiv.org/format/2009.11751">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> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</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/10.1137/1.9781611974973.63">10.1137/1.9781611974973.63 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> BreachRadar: Automatic Detection of Points-of-Compromise </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Araujo%2C+M">Miguel Araujo</a>, <a href="/search/cs?searchtype=author&query=Almeida%2C+M">Miguel Almeida</a>, <a href="/search/cs?searchtype=author&query=Ferreira%2C+J">Jaime Ferreira</a>, <a href="/search/cs?searchtype=author&query=Silva%2C+L">Luis Silva</a>, <a href="/search/cs?searchtype=author&query=Bizarro%2C+P">Pedro Bizarro</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="2009.11751v1-abstract-short" style="display: inline;"> Bank transaction fraud results in over $13B annual losses for banks, merchants, and card holders worldwide. Much of this fraud starts with a Point-of-Compromise (a data breach or a skimming operation) where credit and debit card digital information is stolen, resold, and later used to perform fraud. We introduce this problem and present an automatic Points-of-Compromise (POC) detection procedure.… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2009.11751v1-abstract-full').style.display = 'inline'; document.getElementById('2009.11751v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2009.11751v1-abstract-full" style="display: none;"> Bank transaction fraud results in over $13B annual losses for banks, merchants, and card holders worldwide. Much of this fraud starts with a Point-of-Compromise (a data breach or a skimming operation) where credit and debit card digital information is stolen, resold, and later used to perform fraud. We introduce this problem and present an automatic Points-of-Compromise (POC) detection procedure. BreachRadar is a distributed alternating algorithm that assigns a probability of being compromised to the different possible locations. We implement this method using Apache Spark and show its linear scalability in the number of machines and transactions. BreachRadar is applied to two datasets with billions of real transaction records and fraud labels where we provide multiple examples of real Points-of-Compromise we are able to detect. We further show the effectiveness of our method when injecting Points-of-Compromise in one of these datasets, simultaneously achieving over 90% precision and recall when only 10% of the cards have been victims of fraud. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2009.11751v1-abstract-full').style.display = 'none'; document.getElementById('2009.11751v1-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 September, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2020. </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">9 pages, 10 figures, published in SIAM's 2017 International Conference on Data Mining (SDM17)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2008.06402">arXiv:2008.06402</a> <span> [<a href="https://arxiv.org/pdf/2008.06402">pdf</a>, <a href="https://arxiv.org/format/2008.06402">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="Computer Vision and Pattern Recognition">cs.CV</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">stat.ML</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/10.1145/3372224.3419194">10.1145/3372224.3419194 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> SPINN: Synergistic Progressive Inference of Neural Networks over Device and Cloud </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Laskaridis%2C+S">Stefanos Laskaridis</a>, <a href="/search/cs?searchtype=author&query=Venieris%2C+S+I">Stylianos I. Venieris</a>, <a href="/search/cs?searchtype=author&query=Almeida%2C+M">Mario Almeida</a>, <a href="/search/cs?searchtype=author&query=Leontiadis%2C+I">Ilias Leontiadis</a>, <a href="/search/cs?searchtype=author&query=Lane%2C+N+D">Nicholas D. Lane</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="2008.06402v2-abstract-short" style="display: inline;"> Despite the soaring use of convolutional neural networks (CNNs) in mobile applications, uniformly sustaining high-performance inference on mobile has been elusive due to the excessive computational demands of modern CNNs and the increasing diversity of deployed devices. A popular alternative comprises offloading CNN processing to powerful cloud-based servers. Nevertheless, by relying on the cloud… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2008.06402v2-abstract-full').style.display = 'inline'; document.getElementById('2008.06402v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2008.06402v2-abstract-full" style="display: none;"> Despite the soaring use of convolutional neural networks (CNNs) in mobile applications, uniformly sustaining high-performance inference on mobile has been elusive due to the excessive computational demands of modern CNNs and the increasing diversity of deployed devices. A popular alternative comprises offloading CNN processing to powerful cloud-based servers. Nevertheless, by relying on the cloud to produce outputs, emerging mission-critical and high-mobility applications, such as drone obstacle avoidance or interactive applications, can suffer from the dynamic connectivity conditions and the uncertain availability of the cloud. In this paper, we propose SPINN, a distributed inference system that employs synergistic device-cloud computation together with a progressive inference method to deliver fast and robust CNN inference across diverse settings. The proposed system introduces a novel scheduler that co-optimises the early-exit policy and the CNN splitting at run time, in order to adapt to dynamic conditions and meet user-defined service-level requirements. Quantitative evaluation illustrates that SPINN outperforms its state-of-the-art collaborative inference counterparts by up to 2x in achieved throughput under varying network conditions, reduces the server cost by up to 6.8x and improves accuracy by 20.7% under latency constraints, while providing robust operation under uncertain connectivity conditions and significant energy savings compared to cloud-centric execution. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2008.06402v2-abstract-full').style.display = 'none'; document.getElementById('2008.06402v2-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 August, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 14 August, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2020. </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 the 26th Annual International Conference on Mobile Computing and Networking (MobiCom), 2020</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2005.02443">arXiv:2005.02443</a> <span> [<a href="https://arxiv.org/pdf/2005.02443">pdf</a>, <a href="https://arxiv.org/format/2005.02443">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> </div> </div> <p class="title is-5 mathjax"> A Dataset of Fact-Checked Images Shared on WhatsApp During the Brazilian and Indian Elections </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Reis%2C+J+C+S">Julio C. S. Reis</a>, <a href="/search/cs?searchtype=author&query=Melo%2C+P+d+F">Philipe de Freitas Melo</a>, <a href="/search/cs?searchtype=author&query=Garimella%2C+K">Kiran Garimella</a>, <a href="/search/cs?searchtype=author&query=Almeida%2C+J+M">Jussara M. Almeida</a>, <a href="/search/cs?searchtype=author&query=Eckles%2C+D">Dean Eckles</a>, <a href="/search/cs?searchtype=author&query=Benevenuto%2C+F">Fabr铆cio Benevenuto</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="2005.02443v1-abstract-short" style="display: inline;"> Recently, messaging applications, such as WhatsApp, have been reportedly abused by misinformation campaigns, especially in Brazil and India. A notable form of abuse in WhatsApp relies on several manipulated images and memes containing all kinds of fake stories. In this work, we performed an extensive data collection from a large set of WhatsApp publicly accessible groups and fact-checking agency w… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2005.02443v1-abstract-full').style.display = 'inline'; document.getElementById('2005.02443v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2005.02443v1-abstract-full" style="display: none;"> Recently, messaging applications, such as WhatsApp, have been reportedly abused by misinformation campaigns, especially in Brazil and India. A notable form of abuse in WhatsApp relies on several manipulated images and memes containing all kinds of fake stories. In this work, we performed an extensive data collection from a large set of WhatsApp publicly accessible groups and fact-checking agency websites. This paper opens a novel dataset to the research community containing fact-checked fake images shared through WhatsApp for two distinct scenarios known for the spread of fake news on the platform: the 2018 Brazilian elections and the 2019 Indian elections. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2005.02443v1-abstract-full').style.display = 'none'; document.getElementById('2005.02443v1-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 May, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2020. </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">7 pages. This is a preprint version of an accepted paper on ICWSM'20. Please, consider to cite the conference version instead of this one</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2002.09963">arXiv:2002.09963</a> <span> [<a href="https://arxiv.org/pdf/2002.09963">pdf</a>, <a href="https://arxiv.org/format/2002.09963">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="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Mitigating Class Boundary Label Uncertainty to Reduce Both Model Bias and Variance </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Almeida%2C+M">Matthew Almeida</a>, <a href="/search/cs?searchtype=author&query=Ding%2C+W">Wei Ding</a>, <a href="/search/cs?searchtype=author&query=Crouter%2C+S">Scott Crouter</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+P">Ping Chen</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="2002.09963v1-abstract-short" style="display: inline;"> The study of model bias and variance with respect to decision boundaries is critically important in supervised classification. There is generally a tradeoff between the two, as fine-tuning of the decision boundary of a classification model to accommodate more boundary training samples (i.e., higher model complexity) may improve training accuracy (i.e., lower bias) but hurt generalization against u… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2002.09963v1-abstract-full').style.display = 'inline'; document.getElementById('2002.09963v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2002.09963v1-abstract-full" style="display: none;"> The study of model bias and variance with respect to decision boundaries is critically important in supervised classification. There is generally a tradeoff between the two, as fine-tuning of the decision boundary of a classification model to accommodate more boundary training samples (i.e., higher model complexity) may improve training accuracy (i.e., lower bias) but hurt generalization against unseen data (i.e., higher variance). By focusing on just classification boundary fine-tuning and model complexity, it is difficult to reduce both bias and variance. To overcome this dilemma, we take a different perspective and investigate a new approach to handle inaccuracy and uncertainty in the training data labels, which are inevitable in many applications where labels are conceptual and labeling is performed by human annotators. The process of classification can be undermined by uncertainty in the labels of the training data; extending a boundary to accommodate an inaccurately labeled point will increase both bias and variance. Our novel method can reduce both bias and variance by estimating the pointwise label uncertainty of the training set and accordingly adjusting the training sample weights such that those samples with high uncertainty are weighted down and those with low uncertainty are weighted up. In this way, uncertain samples have a smaller contribution to the objective function of the model's learning algorithm and exert less pull on the decision boundary. In a real-world physical activity recognition case study, the data presents many labeling challenges, and we show that this new approach improves model performance and reduces model variance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2002.09963v1-abstract-full').style.display = 'none'; document.getElementById('2002.09963v1-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 February, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2002.05988">arXiv:2002.05988</a> <span> [<a href="https://arxiv.org/pdf/2002.05988">pdf</a>, <a href="https://arxiv.org/format/2002.05988">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> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</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/10.1145/3394486.3403361">10.1145/3394486.3403361 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Interleaved Sequence RNNs for Fraud Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Branco%2C+B">Bernardo Branco</a>, <a href="/search/cs?searchtype=author&query=Abreu%2C+P">Pedro Abreu</a>, <a href="/search/cs?searchtype=author&query=Gomes%2C+A+S">Ana Sofia Gomes</a>, <a href="/search/cs?searchtype=author&query=Almeida%2C+M+S+C">Mariana S. C. Almeida</a>, <a href="/search/cs?searchtype=author&query=Ascens%C3%A3o%2C+J+T">Jo茫o Tiago Ascens茫o</a>, <a href="/search/cs?searchtype=author&query=Bizarro%2C+P">Pedro Bizarro</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="2002.05988v2-abstract-short" style="display: inline;"> Payment card fraud causes multibillion dollar losses for banks and merchants worldwide, often fueling complex criminal activities. To address this, many real-time fraud detection systems use tree-based models, demanding complex feature engineering systems to efficiently enrich transactions with historical data while complying with millisecond-level latencies. In this work, we do not require thos… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2002.05988v2-abstract-full').style.display = 'inline'; document.getElementById('2002.05988v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2002.05988v2-abstract-full" style="display: none;"> Payment card fraud causes multibillion dollar losses for banks and merchants worldwide, often fueling complex criminal activities. To address this, many real-time fraud detection systems use tree-based models, demanding complex feature engineering systems to efficiently enrich transactions with historical data while complying with millisecond-level latencies. In this work, we do not require those expensive features by using recurrent neural networks and treating payments as an interleaved sequence, where the history of each card is an unbounded, irregular sub-sequence. We present a complete RNN framework to detect fraud in real-time, proposing an efficient ML pipeline from preprocessing to deployment. We show that these feature-free, multi-sequence RNNs outperform state-of-the-art models saving millions of dollars in fraud detection and using fewer computational resources. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2002.05988v2-abstract-full').style.display = 'none'; document.getElementById('2002.05988v2-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 June, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 14 February, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2020. </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">9 pages, 4 figures, to appear in SIGKDD'20 Industry Track</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2002.00580">arXiv:2002.00580</a> <span> [<a href="https://arxiv.org/pdf/2002.00580">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</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/10.5194/isprs-annals-V-1-2020-33-2020">10.5194/isprs-annals-V-1-2020-33-2020 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Super-resolution of multispectral satellite images using convolutional neural networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=M%C3%BCller%2C+M+U">M. U. M眉ller</a>, <a href="/search/cs?searchtype=author&query=Ekhtiari%2C+N">N. Ekhtiari</a>, <a href="/search/cs?searchtype=author&query=Almeida%2C+R+M">R. M. Almeida</a>, <a href="/search/cs?searchtype=author&query=Rieke%2C+C">C. Rieke</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="2002.00580v2-abstract-short" style="display: inline;"> Super-resolution aims at increasing image resolution by algorithmic means and has progressed over the recent years due to advances in the fields of computer vision and deep learning. Convolutional Neural Networks based on a variety of architectures have been applied to the problem, e.g. autoencoders and residual networks. While most research focuses on the processing of photographs consisting only… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2002.00580v2-abstract-full').style.display = 'inline'; document.getElementById('2002.00580v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2002.00580v2-abstract-full" style="display: none;"> Super-resolution aims at increasing image resolution by algorithmic means and has progressed over the recent years due to advances in the fields of computer vision and deep learning. Convolutional Neural Networks based on a variety of architectures have been applied to the problem, e.g. autoencoders and residual networks. While most research focuses on the processing of photographs consisting only of RGB color channels, little work can be found concentrating on multi-band, analytic satellite imagery. Satellite images often include a panchromatic band, which has higher spatial resolution but lower spectral resolution than the other bands. In the field of remote sensing, there is a long tradition of applying pan-sharpening to satellite images, i.e. bringing the multispectral bands to the higher spatial resolution by merging them with the panchromatic band. To our knowledge there are so far no approaches to super-resolution which take advantage of the panchromatic band. In this paper we propose a method to train state-of-the-art CNNs using pairs of lower-resolution multispectral and high-resolution pan-sharpened image tiles in order to create super-resolved analytic images. The derived quality metrics show that the method improves information content of the processed images. We compare the results created by four CNN architectures, with RedNet30 performing best. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2002.00580v2-abstract-full').style.display = 'none'; document.getElementById('2002.00580v2-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> 8 April, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 3 February, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2020. </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">To be published in the ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences: https://www.isprs.org/publications/annals.aspx, proceedings of the XXIV ISPRS Congress, 14-20 June 2020, Nice, France</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68-06 <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.4.3 </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-1-2020, 33-40 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1908.09015">arXiv:1908.09015</a> <span> [<a href="https://arxiv.org/pdf/1908.09015">pdf</a>, <a href="https://arxiv.org/format/1908.09015">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link 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="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> Towards Secure and Decentralized Sharing of IoT Data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Truong%2C+H+T+T">Hien Thi Thu Truong</a>, <a href="/search/cs?searchtype=author&query=Almeida%2C+M">Miguel Almeida</a>, <a href="/search/cs?searchtype=author&query=Karame%2C+G">Ghassan Karame</a>, <a href="/search/cs?searchtype=author&query=Soriente%2C+C">Claudio Soriente</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="1908.09015v1-abstract-short" style="display: inline;"> The Internet of Things (IoT) bears unprecedented security and scalability challenges due to the magnitude of data produced and exchanged by IoT devices and platforms. Some of those challenges are currently being addressed by coupling IoT applications with blockchains. However, current blockchain-backed IoT systems simply use the blockchain to store access control policies, thereby underutilizing t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1908.09015v1-abstract-full').style.display = 'inline'; document.getElementById('1908.09015v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1908.09015v1-abstract-full" style="display: none;"> The Internet of Things (IoT) bears unprecedented security and scalability challenges due to the magnitude of data produced and exchanged by IoT devices and platforms. Some of those challenges are currently being addressed by coupling IoT applications with blockchains. However, current blockchain-backed IoT systems simply use the blockchain to store access control policies, thereby underutilizing the power of blockchain technology. In this paper, we propose a new framework named Sash that couples IoT platforms with blockchain that provides a number of advantages compared to state of the art. In Sash, the blockchain is used to store access control policies and take access control decisions. Therefore, both changes to policies and access requests are correctly enforced and publicly auditable. Further, we devise a ``data marketplace'' by leveraging the ability of blockchains to handle financial transaction and providing ``by design'' remuneration to data producers. Finally, we exploit a special flavor of identity-based encryption to cater for cryptography-enforced access control while minimizing the overhead to distribute decryption keys. We prototype Sash by using the FIWARE open source IoT platform and the Hyperledger Fabric framework as the blockchain back-end. We also evaluate the performance of our prototype and show that it incurs tolerable overhead in realistic deployment settings. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1908.09015v1-abstract-full').style.display = 'none'; document.getElementById('1908.09015v1-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, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1906.10513">arXiv:1906.10513</a> <span> [<a href="https://arxiv.org/pdf/1906.10513">pdf</a>, <a href="https://arxiv.org/format/1906.10513">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> The Role of Compute in Autonomous Aerial Vehicles </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Boroujerdian%2C+B">Behzad Boroujerdian</a>, <a href="/search/cs?searchtype=author&query=Genc%2C+H">Hasan Genc</a>, <a href="/search/cs?searchtype=author&query=Krishnan%2C+S">Srivatsan Krishnan</a>, <a href="/search/cs?searchtype=author&query=Duisterhof%2C+B+P">Bardienus Pieter Duisterhof</a>, <a href="/search/cs?searchtype=author&query=Plancher%2C+B">Brian Plancher</a>, <a href="/search/cs?searchtype=author&query=Mansoorshahi%2C+K">Kayvan Mansoorshahi</a>, <a href="/search/cs?searchtype=author&query=Almeida%2C+M">Marcelino Almeida</a>, <a href="/search/cs?searchtype=author&query=Cui%2C+W">Wenzhi Cui</a>, <a href="/search/cs?searchtype=author&query=Faust%2C+A">Aleksandra Faust</a>, <a href="/search/cs?searchtype=author&query=Reddi%2C+V+J">Vijay Janapa Reddi</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="1906.10513v1-abstract-short" style="display: inline;"> Autonomous-mobile cyber-physical machines are part of our future. Specifically, unmanned-aerial-vehicles have seen a resurgence in activity with use-cases such as package delivery. These systems face many challenges such as their low-endurance caused by limited onboard-energy, hence, improving the mission-time and energy are of importance. Such improvements traditionally are delivered through bett… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1906.10513v1-abstract-full').style.display = 'inline'; document.getElementById('1906.10513v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1906.10513v1-abstract-full" style="display: none;"> Autonomous-mobile cyber-physical machines are part of our future. Specifically, unmanned-aerial-vehicles have seen a resurgence in activity with use-cases such as package delivery. These systems face many challenges such as their low-endurance caused by limited onboard-energy, hence, improving the mission-time and energy are of importance. Such improvements traditionally are delivered through better algorithms. But our premise is that more powerful and efficient onboard-compute should also address the problem. This paper investigates how the compute subsystem, in a cyber-physical mobile machine, such as a Micro Aerial Vehicle, impacts mission-time and energy. Specifically, we pose the question as what is the role of computing for cyber-physical mobile robots? We show that compute and motion are tightly intertwined, hence a close examination of cyber and physical processes and their impact on one another is necessary. We show different impact paths through which compute impacts mission-metrics and examine them using analytical models, simulation, and end-to-end benchmarking. To enable similar studies, we open sourced MAVBench, our tool-set consisting of a closed-loop simulator and a benchmark suite. Our investigations show cyber-physical co-design, a methodology where robot's cyber and physical processes/quantities are developed with one another consideration, similar to hardware-software co-design, is necessary for optimal robot design. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1906.10513v1-abstract-full').style.display = 'none'; document.getElementById('1906.10513v1-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 June, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2019. </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">arXiv admin note: substantial text overlap with arXiv:1905.06388</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1906.06240">arXiv:1906.06240</a> <span> [<a href="https://arxiv.org/pdf/1906.06240">pdf</a>, <a href="https://arxiv.org/format/1906.06240">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link 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="Performance">cs.PF</span> </div> </div> <p class="title is-5 mathjax"> Diffusing Your Mobile Apps: Extending In-Network Function Virtualization to Mobile Function Offloading </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Almeida%2C+M">Mario Almeida</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+L">Liang Wang</a>, <a href="/search/cs?searchtype=author&query=Blackburn%2C+J">Jeremy Blackburn</a>, <a href="/search/cs?searchtype=author&query=Papagiannaki%2C+K">Konstantina Papagiannaki</a>, <a href="/search/cs?searchtype=author&query=Crowcroft%2C+J">Jon Crowcroft</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="1906.06240v1-abstract-short" style="display: inline;"> Motivated by the huge disparity between the limited battery capacity of user devices and the ever-growing energy demands of modern mobile apps, we propose INFv. It is the first offloading system able to cache, migrate and dynamically execute on demand functionality from mobile devices in ISP networks. It aims to bridge this gap by extending the promising NFV paradigm to mobile applications in orde… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1906.06240v1-abstract-full').style.display = 'inline'; document.getElementById('1906.06240v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1906.06240v1-abstract-full" style="display: none;"> Motivated by the huge disparity between the limited battery capacity of user devices and the ever-growing energy demands of modern mobile apps, we propose INFv. It is the first offloading system able to cache, migrate and dynamically execute on demand functionality from mobile devices in ISP networks. It aims to bridge this gap by extending the promising NFV paradigm to mobile applications in order to exploit in-network resources. In this paper, we present the overall design, state-of-the-art technologies adopted, and various engineering details in the INFv system. We also carefully study the deployment configurations by investigating over 20K Google Play apps, as well as thorough evaluations with realistic settings. In addition to a significant improvement in battery life (up to 6.9x energy reduction) and execution time (up to 4x faster), INFv has two distinct advantages over previous systems: 1) a non-intrusive offloading mechanism transparent to existing apps; 2) an inherent framework support to effectively balance computation load and exploit the proximity of in-network resources. Both advantages together enable a scalable and incremental deployment of computation offloading framework in practical ISPs' networks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1906.06240v1-abstract-full').style.display = 'none'; document.getElementById('1906.06240v1-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 June, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1905.07346">arXiv:1905.07346</a> <span> [<a href="https://arxiv.org/pdf/1905.07346">pdf</a>, <a href="https://arxiv.org/format/1905.07346">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="Performance">cs.PF</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</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/10.1145/3325413.3329793">10.1145/3325413.3329793 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> EmBench: Quantifying Performance Variations of Deep Neural Networks across Modern Commodity Devices </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Almeida%2C+M">Mario Almeida</a>, <a href="/search/cs?searchtype=author&query=Laskaridis%2C+S">Stefanos Laskaridis</a>, <a href="/search/cs?searchtype=author&query=Leontiadis%2C+I">Ilias Leontiadis</a>, <a href="/search/cs?searchtype=author&query=Venieris%2C+S+I">Stylianos I. Venieris</a>, <a href="/search/cs?searchtype=author&query=Lane%2C+N+D">Nicholas D. Lane</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="1905.07346v1-abstract-short" style="display: inline;"> In recent years, advances in deep learning have resulted in unprecedented leaps in diverse tasks spanning from speech and object recognition to context awareness and health monitoring. As a result, an increasing number of AI-enabled applications are being developed targeting ubiquitous and mobile devices. While deep neural networks (DNNs) are getting bigger and more complex, they also impose a hea… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1905.07346v1-abstract-full').style.display = 'inline'; document.getElementById('1905.07346v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1905.07346v1-abstract-full" style="display: none;"> In recent years, advances in deep learning have resulted in unprecedented leaps in diverse tasks spanning from speech and object recognition to context awareness and health monitoring. As a result, an increasing number of AI-enabled applications are being developed targeting ubiquitous and mobile devices. While deep neural networks (DNNs) are getting bigger and more complex, they also impose a heavy computational and energy burden on the host devices, which has led to the integration of various specialized processors in commodity devices. Given the broad range of competing DNN architectures and the heterogeneity of the target hardware, there is an emerging need to understand the compatibility between DNN-platform pairs and the expected performance benefits on each platform. This work attempts to demystify this landscape by systematically evaluating a collection of state-of-the-art DNNs on a wide variety of commodity devices. In this respect, we identify potential bottlenecks in each architecture and provide important guidelines that can assist the community in the co-design of more efficient DNNs and accelerators. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1905.07346v1-abstract-full').style.display = 'none'; document.getElementById('1905.07346v1-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 May, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2019. </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 MobiSys 2019: 3rd International Workshop on Embedded and Mobile Deep Learning (EMDL), 2019</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1904.11719">arXiv:1904.11719</a> <span> [<a href="https://arxiv.org/pdf/1904.11719">pdf</a>, <a href="https://arxiv.org/format/1904.11719">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</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/10.1145/3342220.3343657">10.1145/3342220.3343657 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Towards Understanding Political Interactions on Instagram </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Trevisan%2C+M">Martino Trevisan</a>, <a href="/search/cs?searchtype=author&query=Vassio%2C+L">Luca Vassio</a>, <a href="/search/cs?searchtype=author&query=Drago%2C+I">Idilio Drago</a>, <a href="/search/cs?searchtype=author&query=Mellia%2C+M">Marco Mellia</a>, <a href="/search/cs?searchtype=author&query=Murai%2C+F">Fabricio Murai</a>, <a href="/search/cs?searchtype=author&query=Figueiredo%2C+F">Flavio Figueiredo</a>, <a href="/search/cs?searchtype=author&query=da+Silva%2C+A+P+C">Ana Paula Couto da Silva</a>, <a href="/search/cs?searchtype=author&query=Almeida%2C+J+M">Jussara M. Almeida</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="1904.11719v2-abstract-short" style="display: inline;"> Online Social Networks (OSNs) allow personalities and companies to communicate directly with the public, bypassing filters of traditional medias. As people rely on OSNs to stay up-to-date, the political debate has moved online too. We witness the sudden explosion of harsh political debates and the dissemination of rumours in OSNs. Identifying such behaviour requires a deep understanding on how peo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1904.11719v2-abstract-full').style.display = 'inline'; document.getElementById('1904.11719v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1904.11719v2-abstract-full" style="display: none;"> Online Social Networks (OSNs) allow personalities and companies to communicate directly with the public, bypassing filters of traditional medias. As people rely on OSNs to stay up-to-date, the political debate has moved online too. We witness the sudden explosion of harsh political debates and the dissemination of rumours in OSNs. Identifying such behaviour requires a deep understanding on how people interact via OSNs during political debates. We present a preliminary study of interactions in a popular OSN, namely Instagram. We take Italy as a case study in the period before the 2019 European Elections. We observe the activity of top Italian Instagram profiles in different categories: politics, music, sport and show. We record their posts for more than two months, tracking "likes" and comments from users. Results suggest that profiles of politicians attract markedly different interactions than other categories. People tend to comment more, with longer comments, debating for longer time, with a large number of replies, most of which are not explicitly solicited. Moreover, comments tend to come from a small group of very active users. Finally, we witness substantial differences when comparing profiles of different parties. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1904.11719v2-abstract-full').style.display = 'none'; document.getElementById('1904.11719v2-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 May, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 26 April, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2019. </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, 8 figures, Proceedings of the 30th ACM Conference on Hypertext and Social Media, https://dl.acm.org/doi/10.1145/3342220.3343657</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> HT19: Proceedings of the 30th ACM Conference on Hypertext and Social Media. September 2019. Pages 247-251. Association for Computing Machinery </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1901.08317">arXiv:1901.08317</a> <span> [<a href="https://arxiv.org/pdf/1901.08317">pdf</a>, <a href="https://arxiv.org/format/1901.08317">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="Computers and Society">cs.CY</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/10.1007/978-3-030-00949-6_12">10.1007/978-3-030-00949-6_12 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Whole slide image registration for the study of tumor heterogeneity </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Solorzano%2C+L">Leslie Solorzano</a>, <a href="/search/cs?searchtype=author&query=Almeida%2C+G+M">Gabriela M. Almeida</a>, <a href="/search/cs?searchtype=author&query=Mesquita%2C+B">B谩rbara Mesquita</a>, <a href="/search/cs?searchtype=author&query=Martins%2C+D">Diana Martins</a>, <a href="/search/cs?searchtype=author&query=Oliveira%2C+C">Carla Oliveira</a>, <a href="/search/cs?searchtype=author&query=W%C3%A4hlby%2C+C">Carolina W盲hlby</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="1901.08317v1-abstract-short" style="display: inline;"> Consecutive thin sections of tissue samples make it possible to study local variation in e.g. protein expression and tumor heterogeneity by staining for a new protein in each section. In order to compare and correlate patterns of different proteins, the images have to be registered with high accuracy. The problem we want to solve is registration of gigapixel whole slide images (WSI). This presents… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1901.08317v1-abstract-full').style.display = 'inline'; document.getElementById('1901.08317v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1901.08317v1-abstract-full" style="display: none;"> Consecutive thin sections of tissue samples make it possible to study local variation in e.g. protein expression and tumor heterogeneity by staining for a new protein in each section. In order to compare and correlate patterns of different proteins, the images have to be registered with high accuracy. The problem we want to solve is registration of gigapixel whole slide images (WSI). This presents 3 challenges: (i) Images are very large; (ii) Thin sections result in artifacts that make global affine registration prone to very large local errors; (iii) Local affine registration is required to preserve correct tissue morphology (local size, shape and texture). In our approach we compare WSI registration based on automatic and manual feature selection on either the full image or natural sub-regions (as opposed to square tiles). Working with natural sub-regions, in an interactive tool makes it possible to exclude regions containing scientifically irrelevant information. We also present a new way to visualize local registration quality by a Registration Confidence Map (RCM). With this method, intra-tumor heterogeneity and charateristics of the tumor microenvironment can be observed and quantified. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1901.08317v1-abstract-full').style.display = 'none'; document.getElementById('1901.08317v1-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, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2019. </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">MICCAI2018 - Computational Pathology and Ophthalmic Medical Image Analysis - COMPAY</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> vol 11039, 2018, p95-102 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1810.12345">arXiv:1810.12345</a> <span> [<a href="https://arxiv.org/pdf/1810.12345">pdf</a>, <a href="https://arxiv.org/format/1810.12345">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Applications">stat.AP</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/10.1007/978-3-030-01129-1_16">10.1007/978-3-030-01129-1_16 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Analyzing Ideological Communities in Congressional Voting Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ferreira%2C+C+H+G">Carlos H. G. Ferreira</a>, <a href="/search/cs?searchtype=author&query=Matos%2C+B+d+S">Breno de Souza Matos</a>, <a href="/search/cs?searchtype=author&query=Almeida%2C+J+M">Jusssara M. Almeida</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="1810.12345v1-abstract-short" style="display: inline;"> We here study the behavior of political party members aiming at identifying how ideological communities are created and evolve over time in diverse (fragmented and non-fragmented) party systems. Using public voting data of both Brazil and the US, we propose a methodology to identify and characterize ideological communities, their member polarization, and how such communities evolve over time, cove… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1810.12345v1-abstract-full').style.display = 'inline'; document.getElementById('1810.12345v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1810.12345v1-abstract-full" style="display: none;"> We here study the behavior of political party members aiming at identifying how ideological communities are created and evolve over time in diverse (fragmented and non-fragmented) party systems. Using public voting data of both Brazil and the US, we propose a methodology to identify and characterize ideological communities, their member polarization, and how such communities evolve over time, covering a 15-year period. Our results reveal very distinct patterns across the two case studies, in terms of both structural and dynamic properties. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1810.12345v1-abstract-full').style.display = 'none'; document.getElementById('1810.12345v1-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> 29 October, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2018. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1803.03448">arXiv:1803.03448</a> <span> [<a href="https://arxiv.org/pdf/1803.03448">pdf</a>, <a href="https://arxiv.org/format/1803.03448">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> <p class="title is-5 mathjax"> A Family of Droids -- Android Malware Detection via Behavioral Modeling: Static vs Dynamic Analysis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Onwuzurike%2C+L">Lucky Onwuzurike</a>, <a href="/search/cs?searchtype=author&query=Almeida%2C+M">Mario Almeida</a>, <a href="/search/cs?searchtype=author&query=Mariconti%2C+E">Enrico Mariconti</a>, <a href="/search/cs?searchtype=author&query=Blackburn%2C+J">Jeremy Blackburn</a>, <a href="/search/cs?searchtype=author&query=Stringhini%2C+G">Gianluca Stringhini</a>, <a href="/search/cs?searchtype=author&query=De+Cristofaro%2C+E">Emiliano De Cristofaro</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="1803.03448v3-abstract-short" style="display: inline;"> Following the increasing popularity of mobile ecosystems, cybercriminals have increasingly targeted them, designing and distributing malicious apps that steal information or cause harm to the device's owner. Aiming to counter them, detection techniques based on either static or dynamic analysis that model Android malware, have been proposed. While the pros and cons of these analysis techniques are… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1803.03448v3-abstract-full').style.display = 'inline'; document.getElementById('1803.03448v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1803.03448v3-abstract-full" style="display: none;"> Following the increasing popularity of mobile ecosystems, cybercriminals have increasingly targeted them, designing and distributing malicious apps that steal information or cause harm to the device's owner. Aiming to counter them, detection techniques based on either static or dynamic analysis that model Android malware, have been proposed. While the pros and cons of these analysis techniques are known, they are usually compared in the context of their limitations e.g., static analysis is not able to capture runtime behaviors, full code coverage is usually not achieved during dynamic analysis, etc. Whereas, in this paper, we analyze the performance of static and dynamic analysis methods in the detection of Android malware and attempt to compare them in terms of their detection performance, using the same modeling approach. To this end, we build on MaMaDroid, a state-of-the-art detection system that relies on static analysis to create a behavioral model from the sequences of abstracted API calls. Then, aiming to apply the same technique in a dynamic analysis setting, we modify CHIMP, a platform recently proposed to crowdsource human inputs for app testing, in order to extract API calls' sequences from the traces produced while executing the app on a CHIMP virtual device. We call this system AuntieDroid and instantiate it by using both automated (Monkey) and user-generated inputs. We find that combining both static and dynamic analysis yields the best performance, with F-measure reaching 0.92. We also show that static analysis is at least as effective as dynamic analysis, depending on how apps are stimulated during execution, and, finally, investigate the reasons for inconsistent misclassifications across methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1803.03448v3-abstract-full').style.display = 'none'; document.getElementById('1803.03448v3-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 July, 2018; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 March, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2018. </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">A preliminary version of this paper appears in the Proceedings of 16th Annual Conference on Privacy, Security and Trust (PST 2018). This is the full version</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1703.06288">arXiv:1703.06288</a> <span> [<a href="https://arxiv.org/pdf/1703.06288">pdf</a>, <a href="https://arxiv.org/format/1703.06288">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> </div> </div> <p class="title is-5 mathjax"> Gender Matters! Analyzing Global Cultural Gender Preferences for Venues Using Social Sensing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mueller%2C+W">Willi Mueller</a>, <a href="/search/cs?searchtype=author&query=Silva%2C+T+H">Thiago H Silva</a>, <a href="/search/cs?searchtype=author&query=Almeida%2C+J+M">Jussara M Almeida</a>, <a href="/search/cs?searchtype=author&query=Loureiro%2C+A+A+F">Antonio A F Loureiro</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="1703.06288v1-abstract-short" style="display: inline;"> Gender differences is a phenomenon around the world actively researched by social scientists. Traditionally, the data used to support such studies is manually obtained, often through surveys with volunteers. However, due to their inherent high costs because of manual steps, such traditional methods do not quickly scale to large-size studies. We here investigate a particular aspect of gender differ… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1703.06288v1-abstract-full').style.display = 'inline'; document.getElementById('1703.06288v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1703.06288v1-abstract-full" style="display: none;"> Gender differences is a phenomenon around the world actively researched by social scientists. Traditionally, the data used to support such studies is manually obtained, often through surveys with volunteers. However, due to their inherent high costs because of manual steps, such traditional methods do not quickly scale to large-size studies. We here investigate a particular aspect of gender differences: preferences for venues. To that end we explore the use of check-in data collected from Foursquare to estimate cultural gender preferences for venues in the physical world. For that, we first demonstrate that by analyzing the check-in data in various regions of the world we can find significant differences in preferences for specific venues between gender groups. Some of these significant differences reflect well-known cultural patterns. Moreover, we also gathered evidence that our methodology offers useful information about gender preference for venues in a given region in the real world. This suggests that gender and venue preferences observed may not be independent. Our results suggests that our proposed methodology could be a promising tool to support studies on gender preferences for venues at different spatial granularities around the world, being faster and cheaper than traditional methods, besides quickly capturing changes in the real world. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1703.06288v1-abstract-full').style.display = 'none'; document.getElementById('1703.06288v1-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 March, 2017; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2017. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1612.04981">arXiv:1612.04981</a> <span> [<a href="https://arxiv.org/pdf/1612.04981">pdf</a>, <a href="https://arxiv.org/format/1612.04981">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Formal Languages and Automata Theory">cs.FL</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/10.4204/EPTCS.233.4">10.4204/EPTCS.233.4 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Reducing Nondeterministic Tree Automata by Adding Transitions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Almeida%2C+R+M+d+O">Ricardo Manuel de Oliveira Almeida</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="1612.04981v1-abstract-short" style="display: inline;"> We introduce saturation of nondeterministic tree automata, a technique that consists of adding new transitions to an automaton while preserving its language. We implemented our algorithm on minotaut - a module of the tree automata library libvata that reduces the size of automata by merging states and removing superfluous transitions - and we show how saturation can make subsequent merge and trans… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1612.04981v1-abstract-full').style.display = 'inline'; document.getElementById('1612.04981v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1612.04981v1-abstract-full" style="display: none;"> We introduce saturation of nondeterministic tree automata, a technique that consists of adding new transitions to an automaton while preserving its language. We implemented our algorithm on minotaut - a module of the tree automata library libvata that reduces the size of automata by merging states and removing superfluous transitions - and we show how saturation can make subsequent merge and transition-removal operations more effective. Thus we obtain a Ptime algorithm that reduces the size of tree automata even more than before. Additionally, we explore how minotaut alone can play an important role when performing hard operations like complementation, allowing to both obtain smaller complement automata and lower computation times. We then show how saturation can extend this contribution even further. We tested our algorithms on a large collection of automata from applications of libvata in shape analysis, and on different classes of randomly generated automata. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1612.04981v1-abstract-full').style.display = 'none'; document.getElementById('1612.04981v1-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, 2016; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2016. </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">In Proceedings MEMICS 2016, arXiv:1612.04037</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> EPTCS 233, 2016, pp. 33-51 </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=Almeida%2C+M&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Almeida%2C+M&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Almeida%2C+M&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </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