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 1–32 of 32 results for author: <span class="mathjax">Mu, C</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=Mu%2C+C">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="Mu, C"> </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=Mu%2C+C&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="Mu, C"> <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> <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/2411.00887">arXiv:2411.00887</a> <span> [<a href="https://arxiv.org/pdf/2411.00887">pdf</a>, <a href="https://arxiv.org/ps/2411.00887">ps</a>, <a href="https://arxiv.org/format/2411.00887">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Multiagent Systems">cs.MA</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"> Measuring Responsibility in Multi-Agent Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mu%2C+C">Chunyan Mu</a>, <a href="/search/cs?searchtype=author&query=Oren%2C+N">Nir Oren</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="2411.00887v1-abstract-short" style="display: inline;"> We introduce a family of quantitative measures of responsibility in multi-agent planning, building upon the concepts of causal responsibility proposed by Parker et al.~[ParkerGL23]. These concepts are formalised within a variant of probabilistic alternating-time temporal logic. Unlike existing approaches, our framework ascribes responsibility to agents for a given outcome by linking probabilities… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00887v1-abstract-full').style.display = 'inline'; document.getElementById('2411.00887v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.00887v1-abstract-full" style="display: none;"> We introduce a family of quantitative measures of responsibility in multi-agent planning, building upon the concepts of causal responsibility proposed by Parker et al.~[ParkerGL23]. These concepts are formalised within a variant of probabilistic alternating-time temporal logic. Unlike existing approaches, our framework ascribes responsibility to agents for a given outcome by linking probabilities between behaviours and responsibility through three metrics, including an entropy-based measurement of responsibility. This latter measure is the first to capture the causal responsibility properties of outcomes over time, offering an asymptotic measurement that reflects the difficulty of achieving these outcomes. Our approach provides a fresh understanding of responsibility in multi-agent systems, illuminating both the qualitative and quantitative aspects of agents' roles in achieving or preventing outcomes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00887v1-abstract-full').style.display = 'none'; document.getElementById('2411.00887v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 October, 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/2411.00146">arXiv:2411.00146</a> <span> [<a href="https://arxiv.org/pdf/2411.00146">pdf</a>, <a href="https://arxiv.org/ps/2411.00146">ps</a>, <a href="https://arxiv.org/format/2411.00146">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Responsibility-aware Strategic Reasoning in Probabilistic Multi-Agent Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mu%2C+C">Chunyan Mu</a>, <a href="/search/cs?searchtype=author&query=Najib%2C+M">Muhammad Najib</a>, <a href="/search/cs?searchtype=author&query=Oren%2C+N">Nir Oren</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="2411.00146v1-abstract-short" style="display: inline;"> Responsibility plays a key role in the development and deployment of trustworthy autonomous systems. In this paper, we focus on the problem of strategic reasoning in probabilistic multi-agent systems with responsibility-aware agents. We introduce the logic PATL+R, a variant of Probabilistic Alternating-time Temporal Logic. The novelty of PATL+R lies in its incorporation of modalities for causal re… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00146v1-abstract-full').style.display = 'inline'; document.getElementById('2411.00146v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.00146v1-abstract-full" style="display: none;"> Responsibility plays a key role in the development and deployment of trustworthy autonomous systems. In this paper, we focus on the problem of strategic reasoning in probabilistic multi-agent systems with responsibility-aware agents. We introduce the logic PATL+R, a variant of Probabilistic Alternating-time Temporal Logic. The novelty of PATL+R lies in its incorporation of modalities for causal responsibility, providing a framework for responsibility-aware multi-agent strategic reasoning. We present an approach to synthesise joint strategies that satisfy an outcome specified in PATL+R, while optimising the share of expected causal responsibility and reward. This provides a notion of balanced distribution of responsibility and reward gain among agents. To this end, we utilise the Nash equilibrium as the solution concept for our strategic reasoning problem and demonstrate how to compute responsibility-aware Nash equilibrium strategies via a reduction to parametric model checking of concurrent stochastic multi-player games. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00146v1-abstract-full').style.display = 'none'; document.getElementById('2411.00146v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 October, 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/2410.19473">arXiv:2410.19473</a> <span> [<a href="https://arxiv.org/pdf/2410.19473">pdf</a>, <a href="https://arxiv.org/format/2410.19473">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"> A Robust and Efficient Visual-Inertial Initialization with Probabilistic Normal Epipolar Constraint </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mu%2C+C">Changshi Mu</a>, <a href="/search/cs?searchtype=author&query=Feng%2C+D">Daquan Feng</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+Q">Qi Zheng</a>, <a href="/search/cs?searchtype=author&query=Zhuang%2C+Y">Yuan Zhuang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.19473v1-abstract-short" style="display: inline;"> Accurate and robust initialization is essential for Visual-Inertial Odometry (VIO), as poor initialization can severely degrade pose accuracy. During initialization, it is crucial to estimate parameters such as accelerometer bias, gyroscope bias, initial velocity, and gravity, etc. The IMU sensor requires precise estimation of gyroscope bias because gyroscope bias affects rotation, velocity and po… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.19473v1-abstract-full').style.display = 'inline'; document.getElementById('2410.19473v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.19473v1-abstract-full" style="display: none;"> Accurate and robust initialization is essential for Visual-Inertial Odometry (VIO), as poor initialization can severely degrade pose accuracy. During initialization, it is crucial to estimate parameters such as accelerometer bias, gyroscope bias, initial velocity, and gravity, etc. The IMU sensor requires precise estimation of gyroscope bias because gyroscope bias affects rotation, velocity and position. Most existing VIO initialization methods adopt Structure from Motion (SfM) to solve for gyroscope bias. However, SfM is not stable and efficient enough in fast motion or degenerate scenes. To overcome these limitations, we extended the rotation-translation-decoupling framework by adding new uncertainty parameters and optimization modules. First, we adopt a gyroscope bias optimizer that incorporates probabilistic normal epipolar constraints. Second, we fuse IMU and visual measurements to solve for velocity, gravity, and scale efficiently. Finally, we design an additional refinement module that effectively diminishes gravity and scale errors. Extensive initialization tests on the EuRoC dataset show that our method reduces the gyroscope bias and rotation estimation error by an average of 16% and 4% respectively. It also significantly reduces the gravity error, with an average reduction of 29%. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.19473v1-abstract-full').style.display = 'none'; document.getElementById('2410.19473v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.17460">arXiv:2409.17460</a> <span> [<a href="https://arxiv.org/pdf/2409.17460">pdf</a>, <a href="https://arxiv.org/format/2409.17460">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> Towards More Relevant Product Search Ranking Via Large Language Models: An Empirical Study </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qi Liu</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+A">Atul Singh</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jingbo Liu</a>, <a href="/search/cs?searchtype=author&query=Mu%2C+C">Cun Mu</a>, <a href="/search/cs?searchtype=author&query=Yan%2C+Z">Zheng Yan</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="2409.17460v1-abstract-short" style="display: inline;"> Training Learning-to-Rank models for e-commerce product search ranking can be challenging due to the lack of a gold standard of ranking relevance. In this paper, we decompose ranking relevance into content-based and engagement-based aspects, and we propose to leverage Large Language Models (LLMs) for both label and feature generation in model training, primarily aiming to improve the model's predi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17460v1-abstract-full').style.display = 'inline'; document.getElementById('2409.17460v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.17460v1-abstract-full" style="display: none;"> Training Learning-to-Rank models for e-commerce product search ranking can be challenging due to the lack of a gold standard of ranking relevance. In this paper, we decompose ranking relevance into content-based and engagement-based aspects, and we propose to leverage Large Language Models (LLMs) for both label and feature generation in model training, primarily aiming to improve the model's predictive capability for content-based relevance. Additionally, we introduce different sigmoid transformations on the LLM outputs to polarize relevance scores in labeling, enhancing the model's ability to balance content-based and engagement-based relevances and thus prioritize highly relevant items overall. Comprehensive online tests and offline evaluations are also conducted for the proposed design. Our work sheds light on advanced strategies for integrating LLMs into e-commerce product search ranking model training, offering a pathway to more effective and balanced models with improved ranking relevance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17460v1-abstract-full').style.display = 'none'; document.getElementById('2409.17460v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">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">To be published in CIKM 2024 GenAIECommerce Workshop</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.17456">arXiv:2409.17456</a> <span> [<a href="https://arxiv.org/pdf/2409.17456">pdf</a>, <a href="https://arxiv.org/format/2409.17456">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> Long or Short or Both? An Exploration on Lookback Time Windows of Behavioral Features in Product Search Ranking </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qi Liu</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+A">Atul Singh</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jingbo Liu</a>, <a href="/search/cs?searchtype=author&query=Mu%2C+C">Cun Mu</a>, <a href="/search/cs?searchtype=author&query=Yan%2C+Z">Zheng Yan</a>, <a href="/search/cs?searchtype=author&query=Pedersen%2C+J">Jan Pedersen</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="2409.17456v1-abstract-short" style="display: inline;"> Customer shopping behavioral features are core to product search ranking models in eCommerce. In this paper, we investigate the effect of lookback time windows when aggregating these features at the (query, product) level over history. By studying the pros and cons of using long and short time windows, we propose a novel approach to integrating these historical behavioral features of different tim… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17456v1-abstract-full').style.display = 'inline'; document.getElementById('2409.17456v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.17456v1-abstract-full" style="display: none;"> Customer shopping behavioral features are core to product search ranking models in eCommerce. In this paper, we investigate the effect of lookback time windows when aggregating these features at the (query, product) level over history. By studying the pros and cons of using long and short time windows, we propose a novel approach to integrating these historical behavioral features of different time windows. In particular, we address the criticality of using query-level vertical signals in ranking models to effectively aggregate all information from different behavioral features. Anecdotal evidence for the proposed approach is also provided using live product search traffic on Walmart.com. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17456v1-abstract-full').style.display = 'none'; document.getElementById('2409.17456v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">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">Published in ACM SIGIR Workshop on eCommerce 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.15293">arXiv:2408.15293</a> <span> [<a href="https://arxiv.org/pdf/2408.15293">pdf</a>, <a href="https://arxiv.org/format/2408.15293">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="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Learning Granularity Representation for Temporal Knowledge Graph Completion </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jinchuan Zhang</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+T">Tianqi Wan</a>, <a href="/search/cs?searchtype=author&query=Mu%2C+C">Chong Mu</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+G">Guangxi Lu</a>, <a href="/search/cs?searchtype=author&query=Tian%2C+L">Ling Tian</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.15293v1-abstract-short" style="display: inline;"> Temporal Knowledge Graphs (TKGs) incorporate temporal information to reflect the dynamic structural knowledge and evolutionary patterns of real-world facts. Nevertheless, TKGs are still limited in downstream applications due to the problem of incompleteness. Consequently, TKG completion (also known as link prediction) has been widely studied, with recent research focusing on incorporating independ… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.15293v1-abstract-full').style.display = 'inline'; document.getElementById('2408.15293v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.15293v1-abstract-full" style="display: none;"> Temporal Knowledge Graphs (TKGs) incorporate temporal information to reflect the dynamic structural knowledge and evolutionary patterns of real-world facts. Nevertheless, TKGs are still limited in downstream applications due to the problem of incompleteness. Consequently, TKG completion (also known as link prediction) has been widely studied, with recent research focusing on incorporating independent embeddings of time or combining them with entities and relations to form temporal representations. However, most existing methods overlook the impact of history from a multi-granularity aspect. The inherent semantics of human-defined temporal granularities, such as ordinal dates, reveal general patterns to which facts typically adhere. To counter this limitation, this paper proposes \textbf{L}earning \textbf{G}ranularity \textbf{Re}presentation (termed $\mathsf{LGRe}$) for TKG completion. It comprises two main components: Granularity Representation Learning (GRL) and Adaptive Granularity Balancing (AGB). Specifically, GRL employs time-specific multi-layer convolutional neural networks to capture interactions between entities and relations at different granularities. After that, AGB generates adaptive weights for these embeddings according to temporal semantics, resulting in expressive representations of predictions. Moreover, to reflect similar semantics of adjacent timestamps, a temporal loss function is introduced. Extensive experimental results on four event benchmarks demonstrate the effectiveness of $\mathsf{LGRe}$ in learning time-related representations. To ensure reproducibility, our code is available at https://github.com/KcAcoZhang/LGRe. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.15293v1-abstract-full').style.display = 'none'; document.getElementById('2408.15293v1-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, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">15 pages. Accepted at ICONIP 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.10621">arXiv:2405.10621</a> <span> [<a href="https://arxiv.org/pdf/2405.10621">pdf</a>, <a href="https://arxiv.org/format/2405.10621">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Historically Relevant Event Structuring for Temporal Knowledge Graph Reasoning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jinchuan Zhang</a>, <a href="/search/cs?searchtype=author&query=Hui%2C+B">Bei Hui</a>, <a href="/search/cs?searchtype=author&query=Mu%2C+C">Chong Mu</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+M">Ming Sun</a>, <a href="/search/cs?searchtype=author&query=Tian%2C+L">Ling Tian</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2405.10621v1-abstract-short" style="display: inline;"> Temporal Knowledge Graph (TKG) reasoning focuses on predicting events through historical information within snapshots distributed on a timeline. Existing studies mainly concentrate on two perspectives of leveraging the history of TKGs, including capturing evolution of each recent snapshot or correlations among global historical facts. Despite the achieved significant accomplishments, these models… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.10621v1-abstract-full').style.display = 'inline'; document.getElementById('2405.10621v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.10621v1-abstract-full" style="display: none;"> Temporal Knowledge Graph (TKG) reasoning focuses on predicting events through historical information within snapshots distributed on a timeline. Existing studies mainly concentrate on two perspectives of leveraging the history of TKGs, including capturing evolution of each recent snapshot or correlations among global historical facts. Despite the achieved significant accomplishments, these models still fall short of (1) investigating the influences of multi-granularity interactions across recent snapshots and (2) harnessing the expressive semantics of significant links accorded with queries throughout the entire history, especially events exerting a profound impact on the future. These inadequacies restrict representation ability to reflect historical dependencies and future trends thoroughly. To overcome these drawbacks, we propose an innovative TKG reasoning approach towards \textbf{His}torically \textbf{R}elevant \textbf{E}vents \textbf{S}tructuring ($\mathsf{HisRES}$). Concretely, $\mathsf{HisRES}$ comprises two distinctive modules excelling in structuring historically relevant events within TKGs, including a multi-granularity evolutionary encoder that captures structural and temporal dependencies of the most recent snapshots, and a global relevance encoder that concentrates on crucial correlations among events relevant to queries from the entire history. Furthermore, $\mathsf{HisRES}$ incorporates a self-gating mechanism for adaptively merging multi-granularity recent and historically relevant structuring representations. Extensive experiments on four event-based benchmarks demonstrate the state-of-the-art performance of $\mathsf{HisRES}$ and indicate the superiority and effectiveness of structuring historical relevance for TKG reasoning. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.10621v1-abstract-full').style.display = 'none'; document.getElementById('2405.10621v1-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, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.09582">arXiv:2405.09582</a> <span> [<a href="https://arxiv.org/pdf/2405.09582">pdf</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="Image and Video Processing">eess.IV</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/ICECAI62591.2024.10675013">10.1109/ICECAI62591.2024.10675013 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> AD-Aligning: Emulating Human-like Generalization for Cognitive Domain Adaptation in Deep Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+Z">Zhuoying Li</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+B">Bohua Wan</a>, <a href="/search/cs?searchtype=author&query=Mu%2C+C">Cong Mu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+R">Ruzhang Zhao</a>, <a href="/search/cs?searchtype=author&query=Qiu%2C+S">Shushan Qiu</a>, <a href="/search/cs?searchtype=author&query=Yan%2C+C">Chao Yan</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2405.09582v2-abstract-short" style="display: inline;"> Domain adaptation is pivotal for enabling deep learning models to generalize across diverse domains, a task complicated by variations in presentation and cognitive nuances. In this paper, we introduce AD-Aligning, a novel approach that combines adversarial training with source-target domain alignment to enhance generalization capabilities. By pretraining with Coral loss and standard loss, AD-Align… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.09582v2-abstract-full').style.display = 'inline'; document.getElementById('2405.09582v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.09582v2-abstract-full" style="display: none;"> Domain adaptation is pivotal for enabling deep learning models to generalize across diverse domains, a task complicated by variations in presentation and cognitive nuances. In this paper, we introduce AD-Aligning, a novel approach that combines adversarial training with source-target domain alignment to enhance generalization capabilities. By pretraining with Coral loss and standard loss, AD-Aligning aligns target domain statistics with those of the pretrained encoder, preserving robustness while accommodating domain shifts. Through extensive experiments on diverse datasets and domain shift scenarios, including noise-induced shifts and cognitive domain adaptation tasks, we demonstrate AD-Aligning's superior performance compared to existing methods such as Deep Coral and ADDA. Our findings highlight AD-Aligning's ability to emulate the nuanced cognitive processes inherent in human perception, making it a promising solution for real-world applications requiring adaptable and robust domain adaptation strategies. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.09582v2-abstract-full').style.display = 'none'; document.getElementById('2405.09582v2-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 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 14 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by 2024 5th International Conference on Electronic Communication and Artificial Intelligence</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.17270">arXiv:2402.17270</a> <span> [<a href="https://arxiv.org/pdf/2402.17270">pdf</a>, <a href="https://arxiv.org/format/2402.17270">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</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="Multiagent Systems">cs.MA</span> </div> </div> <p class="title is-5 mathjax"> Multi-Agent, Human-Agent and Beyond: A Survey on Cooperation in Social Dilemmas </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mu%2C+C">Chunjiang Mu</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+H">Hao Guo</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yang Chen</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+C">Chen Shen</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+S">Shuyue Hu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zhen Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.17270v2-abstract-short" style="display: inline;"> The study of cooperation within social dilemmas has long been a fundamental topic across various disciplines, including computer science and social science. Recent advancements in Artificial Intelligence (AI) have significantly reshaped this field, offering fresh insights into understanding and enhancing cooperation. This survey examines three key areas at the intersection of AI and cooperation in… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.17270v2-abstract-full').style.display = 'inline'; document.getElementById('2402.17270v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.17270v2-abstract-full" style="display: none;"> The study of cooperation within social dilemmas has long been a fundamental topic across various disciplines, including computer science and social science. Recent advancements in Artificial Intelligence (AI) have significantly reshaped this field, offering fresh insights into understanding and enhancing cooperation. This survey examines three key areas at the intersection of AI and cooperation in social dilemmas. First, focusing on multi-agent cooperation, we review the intrinsic and external motivations that support cooperation among rational agents, and the methods employed to develop effective strategies against diverse opponents. Second, looking into human-agent cooperation, we discuss the current AI algorithms for cooperating with humans and the human biases towards AI agents. Third, we review the emergent field of leveraging AI agents to enhance cooperation among humans. We conclude by discussing future research avenues, such as using large language models, establishing unified theoretical frameworks, revisiting existing theories of human cooperation, and exploring multiple real-world applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.17270v2-abstract-full').style.display = 'none'; document.getElementById('2402.17270v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 27 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.16248">arXiv:2312.16248</a> <span> [<a href="https://arxiv.org/pdf/2312.16248">pdf</a>, <a href="https://arxiv.org/format/2312.16248">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="Digital Libraries">cs.DL</span> </div> </div> <p class="title is-5 mathjax"> XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+W">Wenzhang Liu</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+W">Wenzhe Cai</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+K">Kun Jiang</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+G">Guangran Cheng</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yuanda Wang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jiawei Wang</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+J">Jingyu Cao</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+L">Lele Xu</a>, <a href="/search/cs?searchtype=author&query=Mu%2C+C">Chaoxu Mu</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+C">Changyin Sun</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="2312.16248v1-abstract-short" style="display: inline;"> In this paper, we present XuanCe, a comprehensive and unified deep reinforcement learning (DRL) library designed to be compatible with PyTorch, TensorFlow, and MindSpore. XuanCe offers a wide range of functionalities, including over 40 classical DRL and multi-agent DRL algorithms, with the flexibility to easily incorporate new algorithms and environments. It is a versatile DRL library that support… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.16248v1-abstract-full').style.display = 'inline'; document.getElementById('2312.16248v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.16248v1-abstract-full" style="display: none;"> In this paper, we present XuanCe, a comprehensive and unified deep reinforcement learning (DRL) library designed to be compatible with PyTorch, TensorFlow, and MindSpore. XuanCe offers a wide range of functionalities, including over 40 classical DRL and multi-agent DRL algorithms, with the flexibility to easily incorporate new algorithms and environments. It is a versatile DRL library that supports CPU, GPU, and Ascend, and can be executed on various operating systems such as Ubuntu, Windows, MacOS, and EulerOS. Extensive benchmarks conducted on popular environments including MuJoCo, Atari, and StarCraftII multi-agent challenge demonstrate the library's impressive performance. XuanCe is open-source and can be accessed at https://github.com/agi-brain/xuance.git. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.16248v1-abstract-full').style.display = 'none'; document.getElementById('2312.16248v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 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">16 pages, 4 figures, 32 conferences</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.06550">arXiv:2312.06550</a> <span> [<a href="https://arxiv.org/pdf/2312.06550">pdf</a>, <a href="https://arxiv.org/format/2312.06550">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"> LLM360: Towards Fully Transparent Open-Source LLMs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zhengzhong Liu</a>, <a href="/search/cs?searchtype=author&query=Qiao%2C+A">Aurick Qiao</a>, <a href="/search/cs?searchtype=author&query=Neiswanger%2C+W">Willie Neiswanger</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+H">Hongyi Wang</a>, <a href="/search/cs?searchtype=author&query=Tan%2C+B">Bowen Tan</a>, <a href="/search/cs?searchtype=author&query=Tao%2C+T">Tianhua Tao</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Junbo Li</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yuqi Wang</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+S">Suqi Sun</a>, <a href="/search/cs?searchtype=author&query=Pangarkar%2C+O">Omkar Pangarkar</a>, <a href="/search/cs?searchtype=author&query=Fan%2C+R">Richard Fan</a>, <a href="/search/cs?searchtype=author&query=Gu%2C+Y">Yi Gu</a>, <a href="/search/cs?searchtype=author&query=Miller%2C+V">Victor Miller</a>, <a href="/search/cs?searchtype=author&query=Zhuang%2C+Y">Yonghao Zhuang</a>, <a href="/search/cs?searchtype=author&query=He%2C+G">Guowei He</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Haonan Li</a>, <a href="/search/cs?searchtype=author&query=Koto%2C+F">Fajri Koto</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+L">Liping Tang</a>, <a href="/search/cs?searchtype=author&query=Ranjan%2C+N">Nikhil Ranjan</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+Z">Zhiqiang Shen</a>, <a href="/search/cs?searchtype=author&query=Ren%2C+X">Xuguang Ren</a>, <a href="/search/cs?searchtype=author&query=Iriondo%2C+R">Roberto Iriondo</a>, <a href="/search/cs?searchtype=author&query=Mu%2C+C">Cun Mu</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+Z">Zhiting Hu</a>, <a href="/search/cs?searchtype=author&query=Schulze%2C+M">Mark Schulze</a> , et al. (3 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="2312.06550v1-abstract-short" style="display: inline;"> The recent surge in open-source Large Language Models (LLMs), such as LLaMA, Falcon, and Mistral, provides diverse options for AI practitioners and researchers. However, most LLMs have only released partial artifacts, such as the final model weights or inference code, and technical reports increasingly limit their scope to high-level design choices and surface statistics. These choices hinder prog… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.06550v1-abstract-full').style.display = 'inline'; document.getElementById('2312.06550v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.06550v1-abstract-full" style="display: none;"> The recent surge in open-source Large Language Models (LLMs), such as LLaMA, Falcon, and Mistral, provides diverse options for AI practitioners and researchers. However, most LLMs have only released partial artifacts, such as the final model weights or inference code, and technical reports increasingly limit their scope to high-level design choices and surface statistics. These choices hinder progress in the field by degrading transparency into the training of LLMs and forcing teams to rediscover many details in the training process. We present LLM360, an initiative to fully open-source LLMs, which advocates for all training code and data, model checkpoints, and intermediate results to be made available to the community. The goal of LLM360 is to support open and collaborative AI research by making the end-to-end LLM training process transparent and reproducible by everyone. As a first step of LLM360, we release two 7B parameter LLMs pre-trained from scratch, Amber and CrystalCoder, including their training code, data, intermediate checkpoints, and analyses (at https://www.llm360.ai). We are committed to continually pushing the boundaries of LLMs through this open-source effort. More large-scale and stronger models are underway and will be released in the future. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.06550v1-abstract-full').style.display = 'none'; document.getElementById('2312.06550v1-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 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.03004">arXiv:2312.03004</a> <span> [<a href="https://arxiv.org/pdf/2312.03004">pdf</a>, <a href="https://arxiv.org/format/2312.03004">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> <div 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.eswa.2024.124561">10.1016/j.eswa.2024.124561 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Learning Multi-graph Structure for Temporal Knowledge Graph Reasoning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jinchuan Zhang</a>, <a href="/search/cs?searchtype=author&query=Hui%2C+B">Bei Hui</a>, <a href="/search/cs?searchtype=author&query=Mu%2C+C">Chong Mu</a>, <a href="/search/cs?searchtype=author&query=Tian%2C+L">Ling Tian</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="2312.03004v2-abstract-short" style="display: inline;"> Temporal Knowledge Graph (TKG) reasoning that forecasts future events based on historical snapshots distributed over timestamps is denoted as extrapolation and has gained significant attention. Owing to its extreme versatility and variation in spatial and temporal correlations, TKG reasoning presents a challenging task, demanding efficient capture of concurrent structures and evolutional interacti… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.03004v2-abstract-full').style.display = 'inline'; document.getElementById('2312.03004v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.03004v2-abstract-full" style="display: none;"> Temporal Knowledge Graph (TKG) reasoning that forecasts future events based on historical snapshots distributed over timestamps is denoted as extrapolation and has gained significant attention. Owing to its extreme versatility and variation in spatial and temporal correlations, TKG reasoning presents a challenging task, demanding efficient capture of concurrent structures and evolutional interactions among facts. While existing methods have made strides in this direction, they still fall short of harnessing the diverse forms of intrinsic expressive semantics of TKGs, which encompass entity correlations across multiple timestamps and periodicity of temporal information. This limitation constrains their ability to thoroughly reflect historical dependencies and future trends. In response to these drawbacks, this paper proposes an innovative reasoning approach that focuses on Learning Multi-graph Structure (LMS). Concretely, it comprises three distinct modules concentrating on multiple aspects of graph structure knowledge within TKGs, including concurrent and evolutional patterns along timestamps, query-specific correlations across timestamps, and semantic dependencies of timestamps, which capture TKG features from various perspectives. Besides, LMS incorporates an adaptive gate for merging entity representations both along and across timestamps effectively. Moreover, it integrates timestamp semantics into graph attention calculations and time-aware decoders, in order to impose temporal constraints on events and narrow down prediction scopes with historical statistics. Extensive experimental results on five event-based benchmark datasets demonstrate that LMS outperforms state-of-the-art extrapolation models, indicating the superiority of modeling a multi-graph perspective for TKG reasoning. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.03004v2-abstract-full').style.display = 'none'; document.getElementById('2312.03004v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.02614">arXiv:2310.02614</a> <span> [<a href="https://arxiv.org/pdf/2310.02614">pdf</a>, <a href="https://arxiv.org/ps/2310.02614">ps</a>, <a href="https://arxiv.org/format/2310.02614">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multiagent Systems">cs.MA</span> </div> </div> <p class="title is-5 mathjax"> On Quantified Observability Analysis in Multiagent Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mu%2C+C">Chunyan Mu</a>, <a href="/search/cs?searchtype=author&query=Pang%2C+J">Jun Pang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2310.02614v1-abstract-short" style="display: inline;"> In multiagent systems (MASs), agents' observation upon system behaviours may improve the overall team performance, but may also leak sensitive information to an observer. A quantified observability analysis can thus be useful to assist decision-making in MASs by operators seeking to optimise the relationship between performance effectiveness and information exposure through observations in practic… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.02614v1-abstract-full').style.display = 'inline'; document.getElementById('2310.02614v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.02614v1-abstract-full" style="display: none;"> In multiagent systems (MASs), agents' observation upon system behaviours may improve the overall team performance, but may also leak sensitive information to an observer. A quantified observability analysis can thus be useful to assist decision-making in MASs by operators seeking to optimise the relationship between performance effectiveness and information exposure through observations in practice. This paper presents a novel approach to quantitatively analysing the observability properties in MASs. The concept of opacity is applied to formally express the characterisation of observability in MASs modelled as partially observable multiagent systems. We propose a temporal logic oPATL to reason about agents' observability with quantitative goals, which capture the probability of information transparency of system behaviours to an observer, and develop verification techniques for quantitatively analysing such properties. We implement the approach as an extension of the PRISM model checker, and illustrate its applicability via several examples. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.02614v1-abstract-full').style.display = 'none'; document.getElementById('2310.02614v1-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 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.01414">arXiv:2308.01414</a> <span> [<a href="https://arxiv.org/pdf/2308.01414">pdf</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"> HouYi: An open-source large language model specially designed for renewable energy and carbon neutrality field </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bai%2C+M">Mingliang Bai</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Z">Zhihao Zhou</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+R">Ruidong Wang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Y">Yusheng Yang</a>, <a href="/search/cs?searchtype=author&query=Qin%2C+Z">Zizhen Qin</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yunxiao Chen</a>, <a href="/search/cs?searchtype=author&query=Mu%2C+C">Chunjin Mu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jinfu Liu</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+D">Daren Yu</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="2308.01414v1-abstract-short" style="display: inline;"> Renewable energy is important for achieving carbon neutrality goal. With the great success of Large Language Models (LLMs) like ChatGPT in automatic content generation, LLMs are playing an increasingly important role. However, there has not been a specially designed LLM for renewable energy. Meanwhile, there has not been any dataset of renewable energy for training LLMs. Therefore, this paper publ… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.01414v1-abstract-full').style.display = 'inline'; document.getElementById('2308.01414v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.01414v1-abstract-full" style="display: none;"> Renewable energy is important for achieving carbon neutrality goal. With the great success of Large Language Models (LLMs) like ChatGPT in automatic content generation, LLMs are playing an increasingly important role. However, there has not been a specially designed LLM for renewable energy. Meanwhile, there has not been any dataset of renewable energy for training LLMs. Therefore, this paper published the first open-source Renewable Energy Academic Paper (REAP) dataset for non-commercial LLM research of renewable energy. REAP dataset is collected through searching the title and abstract of 1,168,970 academic literatures from Web of Science. Based on REAP dataset, HouYi model, the first LLM for renewable energy, is developed through finetuning general LLMs. HouYi demonstrated powerful academic paper paragraph generation ability in renewable energy field. Experiments show that its ability to generate academic papers on renewable energy is comparable to ChatGPT, slightly outperforms Claude, ERNIE Bot and SparkDesk, and significantly outperforms open-source LLaMA-13B model. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.01414v1-abstract-full').style.display = 'none'; document.getElementById('2308.01414v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2210.15083">arXiv:2210.15083</a> <span> [<a href="https://arxiv.org/pdf/2210.15083">pdf</a>, <a href="https://arxiv.org/format/2210.15083">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> </div> </div> <p class="title is-5 mathjax"> Deep Learning is Provably Robust to Symmetric Label Noise </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Priebe%2C+C+E">Carey E. Priebe</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+N">Ningyuan Huang</a>, <a href="/search/cs?searchtype=author&query=Villar%2C+S">Soledad Villar</a>, <a href="/search/cs?searchtype=author&query=Mu%2C+C">Cong Mu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+L">Li 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="2210.15083v1-abstract-short" style="display: inline;"> Deep neural networks (DNNs) are capable of perfectly fitting the training data, including memorizing noisy data. It is commonly believed that memorization hurts generalization. Therefore, many recent works propose mitigation strategies to avoid noisy data or correct memorization. In this work, we step back and ask the question: Can deep learning be robust against massive label noise without any mi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.15083v1-abstract-full').style.display = 'inline'; document.getElementById('2210.15083v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2210.15083v1-abstract-full" style="display: none;"> Deep neural networks (DNNs) are capable of perfectly fitting the training data, including memorizing noisy data. It is commonly believed that memorization hurts generalization. Therefore, many recent works propose mitigation strategies to avoid noisy data or correct memorization. In this work, we step back and ask the question: Can deep learning be robust against massive label noise without any mitigation? We provide an affirmative answer for the case of symmetric label noise: We find that certain DNNs, including under-parameterized and over-parameterized models, can tolerate massive symmetric label noise up to the information-theoretic threshold. By appealing to classical statistical theory and universal consistency of DNNs, we prove that for multiclass classification, $L_1$-consistent DNN classifiers trained under symmetric label noise can achieve Bayes optimality asymptotically if the label noise probability is less than $\frac{K-1}{K}$, where $K \ge 2$ is the number of classes. Our results show that for symmetric label noise, no mitigation is necessary for $L_1$-consistent estimators. We conjecture that for general label noise, mitigation strategies that make use of the noisy data will outperform those that ignore the noisy data. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.15083v1-abstract-full').style.display = 'none'; document.getElementById('2210.15083v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 October, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2208.13921">arXiv:2208.13921</a> <span> [<a href="https://arxiv.org/pdf/2208.13921">pdf</a>, <a href="https://arxiv.org/format/2208.13921">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="Statistics Theory">math.ST</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation">stat.CO</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"> Dynamic Network Sampling for Community Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mu%2C+C">Cong Mu</a>, <a href="/search/cs?searchtype=author&query=Park%2C+Y">Youngser Park</a>, <a href="/search/cs?searchtype=author&query=Priebe%2C+C+E">Carey E. Priebe</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="2208.13921v2-abstract-short" style="display: inline;"> We propose a dynamic network sampling scheme to optimize block recovery for stochastic blockmodel (SBM) in the case where it is prohibitively expensive to observe the entire graph. Theoretically, we provide justification of our proposed Chernoff-optimal dynamic sampling scheme via the Chernoff information. Practically, we evaluate the performance, in terms of block recovery, of our method on sever… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.13921v2-abstract-full').style.display = 'inline'; document.getElementById('2208.13921v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2208.13921v2-abstract-full" style="display: none;"> We propose a dynamic network sampling scheme to optimize block recovery for stochastic blockmodel (SBM) in the case where it is prohibitively expensive to observe the entire graph. Theoretically, we provide justification of our proposed Chernoff-optimal dynamic sampling scheme via the Chernoff information. Practically, we evaluate the performance, in terms of block recovery, of our method on several real datasets from different domains. Both theoretically and practically results suggest that our method can identify vertices that have the most impact on block structure so that one can only check whether there are edges between them to save significant resources but still recover the block structure. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.13921v2-abstract-full').style.display = 'none'; document.getElementById('2208.13921v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 December, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 29 August, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 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">18 pages, 8 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2206.14317">arXiv:2206.14317</a> <span> [<a href="https://arxiv.org/pdf/2206.14317">pdf</a>, <a href="https://arxiv.org/ps/2206.14317">ps</a>, <a href="https://arxiv.org/format/2206.14317">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"> Quantitative Verification of Opacity Properties in Security Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mu%2C+C">Chunyan Mu</a>, <a href="/search/cs?searchtype=author&query=Clark%2C+D">David Clark</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="2206.14317v1-abstract-short" style="display: inline;"> We delineate a methodology for the specification and verification of flow security properties expressible in the opacity framework. We propose a logic, OpacTL , for straightforwardly expressing such properties in systems that can be modelled as partially observable labelled transition systems.We develop verification techniques for analysing property opacity with respect to observation notions. Add… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2206.14317v1-abstract-full').style.display = 'inline'; document.getElementById('2206.14317v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2206.14317v1-abstract-full" style="display: none;"> We delineate a methodology for the specification and verification of flow security properties expressible in the opacity framework. We propose a logic, OpacTL , for straightforwardly expressing such properties in systems that can be modelled as partially observable labelled transition systems.We develop verification techniques for analysing property opacity with respect to observation notions. Adding a probabilistic operator to the specification language enables quantitative analysis and verification. This analysis is implemented as an extension to the PRISM model checker and illustrated via a number of examples. Finally, an alternative approach to quantifying the opacity property based on entropy is sketched. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2206.14317v1-abstract-full').style.display = 'none'; document.getElementById('2206.14317v1-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 June, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2205.14299">arXiv:2205.14299</a> <span> [<a href="https://arxiv.org/pdf/2205.14299">pdf</a>, <a href="https://arxiv.org/format/2205.14299">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> </div> </div> <p class="title is-5 mathjax"> Deep Learning with Label Noise: A Hierarchical Approach </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+L">Li Chen</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+N">Ningyuan Huang</a>, <a href="/search/cs?searchtype=author&query=Mu%2C+C">Cong Mu</a>, <a href="/search/cs?searchtype=author&query=Helm%2C+H+S">Hayden S. Helm</a>, <a href="/search/cs?searchtype=author&query=Lytvynets%2C+K">Kate Lytvynets</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+W">Weiwei Yang</a>, <a href="/search/cs?searchtype=author&query=Priebe%2C+C+E">Carey E. Priebe</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="2205.14299v1-abstract-short" style="display: inline;"> Deep neural networks are susceptible to label noise. Existing methods to improve robustness, such as meta-learning and regularization, usually require significant change to the network architecture or careful tuning of the optimization procedure. In this work, we propose a simple hierarchical approach that incorporates a label hierarchy when training the deep learning models. Our approach requires… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.14299v1-abstract-full').style.display = 'inline'; document.getElementById('2205.14299v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2205.14299v1-abstract-full" style="display: none;"> Deep neural networks are susceptible to label noise. Existing methods to improve robustness, such as meta-learning and regularization, usually require significant change to the network architecture or careful tuning of the optimization procedure. In this work, we propose a simple hierarchical approach that incorporates a label hierarchy when training the deep learning models. Our approach requires no change of the network architecture or the optimization procedure. We investigate our hierarchical network through a wide range of simulated and real datasets and various label noise types. Our hierarchical approach improves upon regular deep neural networks in learning with label noise. Combining our hierarchical approach with pre-trained models achieves state-of-the-art performance in real-world noisy datasets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.14299v1-abstract-full').style.display = 'none'; document.getElementById('2205.14299v1-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 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">8 pages, 7 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/2007.02156">arXiv:2007.02156</a> <span> [<a href="https://arxiv.org/pdf/2007.02156">pdf</a>, <a href="https://arxiv.org/format/2007.02156">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="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Statistics Theory">math.ST</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation">stat.CO</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"> On spectral algorithms for community detection in stochastic blockmodel graphs with vertex covariates </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mu%2C+C">Cong Mu</a>, <a href="/search/cs?searchtype=author&query=Mele%2C+A">Angelo Mele</a>, <a href="/search/cs?searchtype=author&query=Hao%2C+L">Lingxin Hao</a>, <a href="/search/cs?searchtype=author&query=Cape%2C+J">Joshua Cape</a>, <a href="/search/cs?searchtype=author&query=Athreya%2C+A">Avanti Athreya</a>, <a href="/search/cs?searchtype=author&query=Priebe%2C+C+E">Carey E. Priebe</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="2007.02156v3-abstract-short" style="display: inline;"> In network inference applications, it is often desirable to detect community structure, namely to cluster vertices into groups, or blocks, according to some measure of similarity. Beyond mere adjacency matrices, many real networks also involve vertex covariates that carry key information about underlying block structure in graphs. To assess the effects of such covariates on block recovery, we pres… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2007.02156v3-abstract-full').style.display = 'inline'; document.getElementById('2007.02156v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2007.02156v3-abstract-full" style="display: none;"> In network inference applications, it is often desirable to detect community structure, namely to cluster vertices into groups, or blocks, according to some measure of similarity. Beyond mere adjacency matrices, many real networks also involve vertex covariates that carry key information about underlying block structure in graphs. To assess the effects of such covariates on block recovery, we present a comparative analysis of two model-based spectral algorithms for clustering vertices in stochastic blockmodel graphs with vertex covariates. The first algorithm uses only the adjacency matrix, and directly estimates the block assignments. The second algorithm incorporates both the adjacency matrix and the vertex covariates into the estimation of block assignments, and moreover quantifies the explicit impact of the vertex covariates on the resulting estimate of the block assignments. We employ Chernoff information to analytically compare the algorithms' performance and derive the information-theoretic Chernoff ratio for certain models of interest. Analytic results and simulations suggest that the second algorithm is often preferred: we can often better estimate the induced block assignments by first estimating the effect of vertex covariates. In addition, real data examples also indicate that the second algorithm has the advantages of revealing underlying block structure and taking observed vertex heterogeneity into account in real applications. Our findings emphasize the importance of distinguishing between observed and unobserved factors that can affect block structure in graphs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2007.02156v3-abstract-full').style.display = 'none'; document.getElementById('2007.02156v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 August, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 July, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 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">17 pages, 7 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/2004.05500">arXiv:2004.05500</a> <span> [<a href="https://arxiv.org/pdf/2004.05500">pdf</a>, <a href="https://arxiv.org/ps/2004.05500">ps</a>, <a href="https://arxiv.org/format/2004.05500">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="Programming Languages">cs.PL</span> </div> </div> <p class="title is-5 mathjax"> Analysing Flow Security Properties in Virtualised Computing Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mu%2C+C">Chunyan Mu</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="2004.05500v1-abstract-short" style="display: inline;"> This paper studies the problem of reasoning about flow security properties in virtualised computing networks with mobility from perspective of formal language. We propose a distributed process algebra CSP_{4v} with security labelled processes for the purpose of formal modelling of virtualised computing systems. Specifically, information leakage can come from observations on process executions, com… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2004.05500v1-abstract-full').style.display = 'inline'; document.getElementById('2004.05500v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2004.05500v1-abstract-full" style="display: none;"> This paper studies the problem of reasoning about flow security properties in virtualised computing networks with mobility from perspective of formal language. We propose a distributed process algebra CSP_{4v} with security labelled processes for the purpose of formal modelling of virtualised computing systems. Specifically, information leakage can come from observations on process executions, communications and from cache side channels in the virtualised environment. We describe a cache flow policy to identify such flows. A type system of the language is presented to enforce the flow policy and control the leakage introduced by observing behaviours of communicating processes and behaviours of virtual machine (VM) instances during accessing shared memory cache. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2004.05500v1-abstract-full').style.display = 'none'; document.getElementById('2004.05500v1-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 April, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1911.02825">arXiv:1911.02825</a> <span> [<a href="https://arxiv.org/pdf/1911.02825">pdf</a>, <a href="https://arxiv.org/format/1911.02825">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> </div> </div> <p class="title is-5 mathjax"> Improving Grammatical Error Correction with Machine Translation Pairs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhou%2C+W">Wangchunshu Zhou</a>, <a href="/search/cs?searchtype=author&query=Ge%2C+T">Tao Ge</a>, <a href="/search/cs?searchtype=author&query=Mu%2C+C">Chang Mu</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+K">Ke Xu</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+F">Furu Wei</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+M">Ming Zhou</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="1911.02825v2-abstract-short" style="display: inline;"> We propose a novel data synthesis method to generate diverse error-corrected sentence pairs for improving grammatical error correction, which is based on a pair of machine translation models of different qualities (i.e., poor and good). The poor translation model resembles the ESL (English as a second language) learner and tends to generate translations of low quality in terms of fluency and gramm… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1911.02825v2-abstract-full').style.display = 'inline'; document.getElementById('1911.02825v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1911.02825v2-abstract-full" style="display: none;"> We propose a novel data synthesis method to generate diverse error-corrected sentence pairs for improving grammatical error correction, which is based on a pair of machine translation models of different qualities (i.e., poor and good). The poor translation model resembles the ESL (English as a second language) learner and tends to generate translations of low quality in terms of fluency and grammatical correctness, while the good translation model generally generates fluent and grammatically correct translations. We build the poor and good translation model with phrase-based statistical machine translation model with decreased language model weight and neural machine translation model respectively. By taking the pair of their translations of the same sentences in a bridge language as error-corrected sentence pairs, we can construct unlimited pseudo parallel data. Our approach is capable of generating diverse fluency-improving patterns without being limited by the pre-defined rule set and the seed error-corrected data. Experimental results demonstrate the effectiveness of our approach and show that it can be combined with other synthetic data sources to yield further improvements. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1911.02825v2-abstract-full').style.display = 'none'; document.getElementById('1911.02825v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 November, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 7 November, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 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">EMNLP 2020 Findings</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1906.10095">arXiv:1906.10095</a> <span> [<a href="https://arxiv.org/pdf/1906.10095">pdf</a>, <a href="https://arxiv.org/ps/1906.10095">ps</a>, <a href="https://arxiv.org/format/1906.10095">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="Information Retrieval">cs.IR</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"> An Empirical Comparison of FAISS and FENSHSES for Nearest Neighbor Search in Hamming Space </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mu%2C+C">Cun Mu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+B">Binwei Yang</a>, <a href="/search/cs?searchtype=author&query=Yan%2C+Z">Zheng Yan</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="1906.10095v2-abstract-short" style="display: inline;"> In this paper, we compare the performances of FAISS and FENSHSES on nearest neighbor search in Hamming space--a fundamental task with ubiquitous applications in nowadays eCommerce. Comprehensive evaluations are made in terms of indexing speed, search latency and RAM consumption. This comparison is conducted towards a better understanding on trade-offs between nearest neighbor search systems implem… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1906.10095v2-abstract-full').style.display = 'inline'; document.getElementById('1906.10095v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1906.10095v2-abstract-full" style="display: none;"> In this paper, we compare the performances of FAISS and FENSHSES on nearest neighbor search in Hamming space--a fundamental task with ubiquitous applications in nowadays eCommerce. Comprehensive evaluations are made in terms of indexing speed, search latency and RAM consumption. This comparison is conducted towards a better understanding on trade-offs between nearest neighbor search systems implemented in main memory and the ones implemented in secondary memory, which is largely unaddressed in literature. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1906.10095v2-abstract-full').style.display = 'none'; document.getElementById('1906.10095v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 July, 2019; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 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">SIGIR eCom'19</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1902.08498">arXiv:1902.08498</a> <span> [<a href="https://arxiv.org/pdf/1902.08498">pdf</a>, <a href="https://arxiv.org/format/1902.08498">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</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> <p class="title is-5 mathjax"> Fast and Exact Nearest Neighbor Search in Hamming Space on Full-Text Search Engines </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mu%2C+C">Cun Mu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+J">Jun Zhao</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+G">Guang Yang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+B">Binwei Yang</a>, <a href="/search/cs?searchtype=author&query=Yan%2C+Z">Zheng Yan</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="1902.08498v2-abstract-short" style="display: inline;"> A growing interest has been witnessed recently from both academia and industry in building nearest neighbor search (NNS) solutions on top of full-text search engines. Compared with other NNS systems, such solutions are capable of effectively reducing main memory consumption, coherently supporting multi-model search and being immediately ready for production deployment. In this paper, we continue t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1902.08498v2-abstract-full').style.display = 'inline'; document.getElementById('1902.08498v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1902.08498v2-abstract-full" style="display: none;"> A growing interest has been witnessed recently from both academia and industry in building nearest neighbor search (NNS) solutions on top of full-text search engines. Compared with other NNS systems, such solutions are capable of effectively reducing main memory consumption, coherently supporting multi-model search and being immediately ready for production deployment. In this paper, we continue the journey to explore specifically how to empower full-text search engines with fast and exact NNS in Hamming space (i.e., the set of binary codes). By revisiting three techniques (bit operation, subs-code filtering and data preprocessing with permutation) in information retrieval literature, we develop a novel engineering solution for full-text search engines to efficiently accomplish this special but important NNS task. In the experiment, we show that our proposed approach enables full-text search engines to achieve significant speed-ups over its state-of-the-art term match approach for NNS within binary codes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1902.08498v2-abstract-full').style.display = 'none'; document.getElementById('1902.08498v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 July, 2019; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 February, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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">A shorter version of the paper is accepted by SISAP 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/1809.10210">arXiv:1809.10210</a> <span> [<a href="https://arxiv.org/pdf/1809.10210">pdf</a>, <a href="https://arxiv.org/ps/1809.10210">ps</a>, <a href="https://arxiv.org/format/1809.10210">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="Optimization and Control">math.OC</span> </div> </div> <p class="title is-5 mathjax"> A Machine Learning Approach to Shipping Box Design </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+G">Guang Yang</a>, <a href="/search/cs?searchtype=author&query=Mu%2C+C">Cun Mu</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="1809.10210v3-abstract-short" style="display: inline;"> Having the right assortment of shipping boxes in the fulfillment warehouse to pack and ship customer's online orders is an indispensable and integral part of nowadays eCommerce business, as it will not only help maintain a profitable business but also create great experiences for customers. However, it is an extremely challenging operations task to strategically select the best combination of tens… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1809.10210v3-abstract-full').style.display = 'inline'; document.getElementById('1809.10210v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1809.10210v3-abstract-full" style="display: none;"> Having the right assortment of shipping boxes in the fulfillment warehouse to pack and ship customer's online orders is an indispensable and integral part of nowadays eCommerce business, as it will not only help maintain a profitable business but also create great experiences for customers. However, it is an extremely challenging operations task to strategically select the best combination of tens of box sizes from thousands of feasible ones to be responsible for hundreds of thousands of orders daily placed on millions of inventory products. In this paper, we present a machine learning approach to tackle the task by formulating the box design problem prescriptively as a generalized version of weighted $k$-medoids clustering problem, where the parameters are estimated through a variety of descriptive analytics. We test this machine learning approach on fulfillment data collected from Walmart U.S. eCommerce, and our approach is shown to be capable of improving the box utilization rate by more than $10\%$. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1809.10210v3-abstract-full').style.display = 'none'; document.getElementById('1809.10210v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 March, 2019; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 26 September, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 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">Accepted by 2019 Intelligent Systems Conference (A shorter version of the paper is presented at the 13th INFORMS Workshop on Data Mining and Decision Analytics)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1806.08896">arXiv:1806.08896</a> <span> [<a href="https://arxiv.org/pdf/1806.08896">pdf</a>, <a href="https://arxiv.org/format/1806.08896">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Towards Practical Visual Search Engine within Elasticsearch </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mu%2C+C">Cun Mu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+J">Jun Zhao</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+G">Guang Yang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jing Zhang</a>, <a href="/search/cs?searchtype=author&query=Yan%2C+Z">Zheng Yan</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="1806.08896v3-abstract-short" style="display: inline;"> In this paper, we describe our end-to-end content-based image retrieval system built upon Elasticsearch, a well-known and popular textual search engine. As far as we know, this is the first time such a system has been implemented in eCommerce, and our efforts have turned out to be highly worthwhile. We end up with a novel and exciting visual search solution that is extremely easy to be deployed, d… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1806.08896v3-abstract-full').style.display = 'inline'; document.getElementById('1806.08896v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1806.08896v3-abstract-full" style="display: none;"> In this paper, we describe our end-to-end content-based image retrieval system built upon Elasticsearch, a well-known and popular textual search engine. As far as we know, this is the first time such a system has been implemented in eCommerce, and our efforts have turned out to be highly worthwhile. We end up with a novel and exciting visual search solution that is extremely easy to be deployed, distributed, scaled and monitored in a cost-friendly manner. Moreover, our platform is intrinsically flexible in supporting multimodal searches, where visual and textual information can be jointly leveraged in retrieval. The core idea is to encode image feature vectors into a collection of string tokens in a way such that closer vectors will share more string tokens in common. By doing that, we can utilize Elasticsearch to efficiently retrieve similar images based on similarities within encoded sting tokens. As part of the development, we propose a novel vector to string encoding method, which is shown to substantially outperform the previous ones in terms of both precision and latency. First-hand experiences in implementing this Elasticsearch-based platform are extensively addressed, which should be valuable to practitioners also interested in building visual search engine on top of Elasticsearch. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1806.08896v3-abstract-full').style.display = 'none'; document.getElementById('1806.08896v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 March, 2019; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 June, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 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">Accepted by SIGIR eCom'18</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1804.00306">arXiv:1804.00306</a> <span> [<a href="https://arxiv.org/pdf/1804.00306">pdf</a>, <a href="https://arxiv.org/format/1804.00306">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="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"> Revisiting Skip-Gram Negative Sampling Model with Rectification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mu%2C+C">Cun Mu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+G">Guang Yang</a>, <a href="/search/cs?searchtype=author&query=Yan%2C+Z">Zheng Yan</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="1804.00306v2-abstract-short" style="display: inline;"> We revisit skip-gram negative sampling (SGNS), one of the most popular neural-network based approaches to learning distributed word representation. We first point out the ambiguity issue undermining the SGNS model, in the sense that the word vectors can be entirely distorted without changing the objective value. To resolve the issue, we investigate the intrinsic structures in solution that a good… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1804.00306v2-abstract-full').style.display = 'inline'; document.getElementById('1804.00306v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1804.00306v2-abstract-full" style="display: none;"> We revisit skip-gram negative sampling (SGNS), one of the most popular neural-network based approaches to learning distributed word representation. We first point out the ambiguity issue undermining the SGNS model, in the sense that the word vectors can be entirely distorted without changing the objective value. To resolve the issue, we investigate the intrinsic structures in solution that a good word embedding model should deliver. Motivated by this, we rectify the SGNS model with quadratic regularization, and show that this simple modification suffices to structure the solution in the desired manner. A theoretical justification is presented, which provides novel insights into quadratic regularization . Preliminary experiments are also conducted on Google's analytical reasoning task to support the modified SGNS model. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1804.00306v2-abstract-full').style.display = 'none'; document.getElementById('1804.00306v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 January, 2019; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 1 April, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 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">Accepted for publication in the proceedings of 2019 Computing Conference</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1608.01686">arXiv:1608.01686</a> <span> [<a href="https://arxiv.org/pdf/1608.01686">pdf</a>, <a href="https://arxiv.org/format/1608.01686">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Sparse Filtered SIRT for Electron Tomography </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mu%2C+C">Chen Mu</a>, <a href="/search/cs?searchtype=author&query=Park%2C+C">Chiwoo Park</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="1608.01686v2-abstract-short" style="display: inline;"> Electron tomographic reconstruction is a method for obtaining a three-dimensional image of a specimen with a series of two dimensional microscope images taken from different viewing angles. Filtered backprojection, one of the most popular tomographic reconstruction methods, does not work well under the existence of image noises and missing wedges. This paper presents a new approach to largely miti… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1608.01686v2-abstract-full').style.display = 'inline'; document.getElementById('1608.01686v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1608.01686v2-abstract-full" style="display: none;"> Electron tomographic reconstruction is a method for obtaining a three-dimensional image of a specimen with a series of two dimensional microscope images taken from different viewing angles. Filtered backprojection, one of the most popular tomographic reconstruction methods, does not work well under the existence of image noises and missing wedges. This paper presents a new approach to largely mitigate the effect of noises and missing wedges. We propose a novel filtered backprojection that optimizes the filter of the backprojection operator in terms of a reconstruction error. This data-dependent filter adaptively chooses the spectral domains of signals and noises, suppressing the noise frequency bands, so it is very effective in denoising. We also propose the new filtered backprojection embedded within the simultaneous iterative reconstruction iteration for mitigating the effect of missing wedges. Our numerical study is presented to show the performance gain of the proposed approach over the state-of-the-art. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1608.01686v2-abstract-full').style.display = 'none'; document.getElementById('1608.01686v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 July, 2018; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 August, 2016; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2016. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> I.4.3; I.4.5 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1405.6163">arXiv:1405.6163</a> <span> [<a href="https://arxiv.org/pdf/1405.6163">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Other Computer Science">cs.OH</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/10.4156/jcit.vol7.issue20.14">10.4156/jcit.vol7.issue20.14 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Revised Version of a JCIT Paper-Comparison of Feature Point Extraction Algorithms for Vision Based Autonomous Aerial Refueling </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+B">Borui Li</a>, <a href="/search/cs?searchtype=author&query=Mu%2C+C">Chundi Mu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+T">Tao Wang</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+Q">Qian Peng</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="1405.6163v2-abstract-short" style="display: inline;"> This is a revised version of our paper published in Journal of Convergence Information Technology(JCIT): "Comparison of Feature Point Extraction Algorithms for Vision Based Autonomous Aerial Refueling". We corrected some errors including measurement unit errors, spelling errors and so on. Since the published papers in JCIT are not allowed to be modified, we submit the revised version to arXiv.org… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1405.6163v2-abstract-full').style.display = 'inline'; document.getElementById('1405.6163v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1405.6163v2-abstract-full" style="display: none;"> This is a revised version of our paper published in Journal of Convergence Information Technology(JCIT): "Comparison of Feature Point Extraction Algorithms for Vision Based Autonomous Aerial Refueling". We corrected some errors including measurement unit errors, spelling errors and so on. Since the published papers in JCIT are not allowed to be modified, we submit the revised version to arXiv.org to make the paper more rigorous and not to confuse other researchers. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1405.6163v2-abstract-full').style.display = 'none'; document.getElementById('1405.6163v2-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 June, 2014; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 28 April, 2014; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2014. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Journal of Convergence Information Technology. 2012, 7(20): 108-118 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1404.7760">arXiv:1404.7760</a> <span> [<a href="https://arxiv.org/pdf/1404.7760">pdf</a>, <a href="https://arxiv.org/ps/1404.7760">ps</a>, <a href="https://arxiv.org/format/1404.7760">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="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> A Flow Sensitive Security Model for Cloud Computing Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zeng%2C+W">Wen Zeng</a>, <a href="/search/cs?searchtype=author&query=Mu%2C+C">Chunyan Mu</a>, <a href="/search/cs?searchtype=author&query=Koutny%2C+M">Maciej Koutny</a>, <a href="/search/cs?searchtype=author&query=Watson%2C+P">Paul Watson</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="1404.7760v1-abstract-short" style="display: inline;"> The extent and importance of cloud computing is rapidly increasing due to the ever increasing demand for internet services and communications. Instead of building individual information technology infrastructure to host databases or software, a third party can host them in its large server clouds. Large organizations may wish to keep sensitive information on their more restricted servers rather th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1404.7760v1-abstract-full').style.display = 'inline'; document.getElementById('1404.7760v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1404.7760v1-abstract-full" style="display: none;"> The extent and importance of cloud computing is rapidly increasing due to the ever increasing demand for internet services and communications. Instead of building individual information technology infrastructure to host databases or software, a third party can host them in its large server clouds. Large organizations may wish to keep sensitive information on their more restricted servers rather than in the public cloud. This has led to the introduction of federated cloud computing (FCC) in which both public and private cloud computing resources are used. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1404.7760v1-abstract-full').style.display = 'none'; document.getElementById('1404.7760v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 April, 2014; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2014. </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">EDCC-2014, EDSoS-2014</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1403.7588">arXiv:1403.7588</a> <span> [<a href="https://arxiv.org/pdf/1403.7588">pdf</a>, <a href="https://arxiv.org/format/1403.7588">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</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="Numerical Analysis">math.NA</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/10.1137/15M101628X">10.1137/15M101628X <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Scalable Robust Matrix Recovery: Frank-Wolfe Meets Proximal Methods </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mu%2C+C">Cun Mu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yuqian Zhang</a>, <a href="/search/cs?searchtype=author&query=Wright%2C+J">John Wright</a>, <a href="/search/cs?searchtype=author&query=Goldfarb%2C+D">Donald Goldfarb</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="1403.7588v2-abstract-short" style="display: inline;"> Recovering matrices from compressive and grossly corrupted observations is a fundamental problem in robust statistics, with rich applications in computer vision and machine learning. In theory, under certain conditions, this problem can be solved in polynomial time via a natural convex relaxation, known as Compressive Principal Component Pursuit (CPCP). However, all existing provable algorithms fo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1403.7588v2-abstract-full').style.display = 'inline'; document.getElementById('1403.7588v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1403.7588v2-abstract-full" style="display: none;"> Recovering matrices from compressive and grossly corrupted observations is a fundamental problem in robust statistics, with rich applications in computer vision and machine learning. In theory, under certain conditions, this problem can be solved in polynomial time via a natural convex relaxation, known as Compressive Principal Component Pursuit (CPCP). However, all existing provable algorithms for CPCP suffer from superlinear per-iteration cost, which severely limits their applicability to large scale problems. In this paper, we propose provable, scalable and efficient methods to solve CPCP with (essentially) linear per-iteration cost. Our method combines classical ideas from Frank-Wolfe and proximal methods. In each iteration, we mainly exploit Frank-Wolfe to update the low-rank component with rank-one SVD and exploit the proximal step for the sparse term. Convergence results and implementation details are also discussed. We demonstrate the scalability of the proposed approach with promising numerical experiments on visual data. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1403.7588v2-abstract-full').style.display = 'none'; document.getElementById('1403.7588v2-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 May, 2017; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 29 March, 2014; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2014. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> SIAM Journal on Scientific Computing, 2016, Vol. 38, No. 5 : pp. A3291-A3317 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1307.5870">arXiv:1307.5870</a> <span> [<a href="https://arxiv.org/pdf/1307.5870">pdf</a>, <a href="https://arxiv.org/format/1307.5870">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> </div> </div> <p class="title is-5 mathjax"> Square Deal: Lower Bounds and Improved Relaxations for Tensor Recovery </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mu%2C+C">Cun Mu</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+B">Bo Huang</a>, <a href="/search/cs?searchtype=author&query=Wright%2C+J">John Wright</a>, <a href="/search/cs?searchtype=author&query=Goldfarb%2C+D">Donald Goldfarb</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="1307.5870v2-abstract-short" style="display: inline;"> Recovering a low-rank tensor from incomplete information is a recurring problem in signal processing and machine learning. The most popular convex relaxation of this problem minimizes the sum of the nuclear norms of the unfoldings of the tensor. We show that this approach can be substantially suboptimal: reliably recovering a $K$-way tensor of length $n$ and Tucker rank $r$ from Gaussian measureme… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1307.5870v2-abstract-full').style.display = 'inline'; document.getElementById('1307.5870v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1307.5870v2-abstract-full" style="display: none;"> Recovering a low-rank tensor from incomplete information is a recurring problem in signal processing and machine learning. The most popular convex relaxation of this problem minimizes the sum of the nuclear norms of the unfoldings of the tensor. We show that this approach can be substantially suboptimal: reliably recovering a $K$-way tensor of length $n$ and Tucker rank $r$ from Gaussian measurements requires $惟(r n^{K-1})$ observations. In contrast, a certain (intractable) nonconvex formulation needs only $O(r^K + nrK)$ observations. We introduce a very simple, new convex relaxation, which partially bridges this gap. Our new formulation succeeds with $O(r^{\lfloor K/2 \rfloor}n^{\lceil K/2 \rceil})$ observations. While these results pertain to Gaussian measurements, simulations strongly suggest that the new norm also outperforms the sum of nuclear norms for tensor completion from a random subset of entries. Our lower bound for the sum-of-nuclear-norms model follows from a new result on recovering signals with multiple sparse structures (e.g. sparse, low rank), which perhaps surprisingly demonstrates the significant suboptimality of the commonly used recovery approach via minimizing the sum of individual sparsity inducing norms (e.g. $l_1$, nuclear norm). Our new formulation for low-rank tensor recovery however opens the possibility in reducing the sample complexity by exploiting several structures jointly. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1307.5870v2-abstract-full').style.display = 'none'; document.getElementById('1307.5870v2-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 August, 2013; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 July, 2013; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2013. </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">Slight modifications are made in this second version (mainly, Lemma 5)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1307.1437">arXiv:1307.1437</a> <span> [<a href="https://arxiv.org/pdf/1307.1437">pdf</a>, <a href="https://arxiv.org/format/1307.1437">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Toward Guaranteed Illumination Models for Non-Convex Objects </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yuqian Zhang</a>, <a href="/search/cs?searchtype=author&query=Mu%2C+C">Cun Mu</a>, <a href="/search/cs?searchtype=author&query=Kuo%2C+H">Han-wen Kuo</a>, <a href="/search/cs?searchtype=author&query=Wright%2C+J">John Wright</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="1307.1437v1-abstract-short" style="display: inline;"> Illumination variation remains a central challenge in object detection and recognition. Existing analyses of illumination variation typically pertain to convex, Lambertian objects, and guarantee quality of approximation in an average case sense. We show that it is possible to build V(vertex)-description convex cone models with worst-case performance guarantees, for non-convex Lambertian objects. N… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1307.1437v1-abstract-full').style.display = 'inline'; document.getElementById('1307.1437v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1307.1437v1-abstract-full" style="display: none;"> Illumination variation remains a central challenge in object detection and recognition. Existing analyses of illumination variation typically pertain to convex, Lambertian objects, and guarantee quality of approximation in an average case sense. We show that it is possible to build V(vertex)-description convex cone models with worst-case performance guarantees, for non-convex Lambertian objects. Namely, a natural verification test based on the angle to the constructed cone guarantees to accept any image which is sufficiently well-approximated by an image of the object under some admissible lighting condition, and guarantees to reject any image that does not have a sufficiently good approximation. The cone models are generated by sampling point illuminations with sufficient density, which follows from a new perturbation bound for point images in the Lambertian model. As the number of point images required for guaranteed verification may be large, we introduce a new formulation for cone preserving dimensionality reduction, which leverages tools from sparse and low-rank decomposition to reduce the complexity, while controlling the approximation error with respect to the original cone. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1307.1437v1-abstract-full').style.display = 'none'; document.getElementById('1307.1437v1-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 July, 2013; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2013. </p> </li> </ol> <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