Search | arXiv e-print repository

<!DOCTYPE html> <html lang="en"> <head> <meta charset="utf-8"/> <meta name="viewport" content="width=device-width, initial-scale=1"/>  <link rel="apple-touch-icon" sizes="180x180" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/apple-touch-icon.png"> <link rel="icon" type="image/png" sizes="32x32" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-32x32.png"> <link rel="icon" type="image/png" sizes="16x16" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-16x16.png"> <link rel="manifest" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/site.webmanifest"> <link rel="mask-icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/safari-pinned-tab.svg" color="#b31b1b"> <link rel="shortcut icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon.ico"> <meta name="msapplication-TileColor" content="#b31b1b"> <meta name="msapplication-config" content="images/icons/browserconfig.xml"> <meta name="theme-color" content="#b31b1b">  <title>Search | arXiv e-print repository</title> <script defer src="https://static.arxiv.org/static/base/1.0.0a5/fontawesome-free-5.11.2-web/js/all.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/base/1.0.0a5/css/arxivstyle.css" /> <script type="text/x-mathjax-config"> MathJax.Hub.Config({ messageStyle: "none", extensions: ["tex2jax.js"], jax: ["input/TeX", "output/HTML-CSS"], tex2jax: { inlineMath: [ ['$','$'], ["\$","\$"] ], displayMath: [ ['$$','$$'], ["\\[","\\]"] ], processEscapes: true, ignoreClass: '.*', processClass: 'mathjax.*' }, TeX: { extensions: ["AMSmath.js", "AMSsymbols.js", "noErrors.js"], noErrors: { inlineDelimiters: ["$","$"], multiLine: false, style: { "font-size": "normal", "border": "" } } }, "HTML-CSS": { availableFonts: ["TeX"] } }); </script> <script src='//static.arxiv.org/MathJax-2.7.3/MathJax.js'></script> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/notification.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/bulma-tooltip.min.css" /> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/search.css" /> <script src="https://code.jquery.com/jquery-3.2.1.slim.min.js" integrity="sha256-k2WSCIexGzOj3Euiig+TlR8gA0EmPjuc79OEeY5L45g=" crossorigin="anonymous"></script> <script src="https://static.arxiv.org/static/search/0.5.6/js/fieldset.js"></script> <style> radio#cf-customfield_11400 { display: none; } </style> </head> <body> <header><a href="#main-container" class="is-sr-only">Skip to main content</a>  <div class="attribution level is-marginless" role="banner"> <div class="level-left"> <a class="level-item" href="https://cornell.edu/"><img src="https://static.arxiv.org/static/base/1.0.0a5/images/cornell-reduced-white-SMALL.svg" alt="Cornell University" width="200" aria-label="logo" /></a> </div> <div class="level-right is-marginless"><p class="sponsors level-item is-marginless"><span id="support-ack-url">We gratefully acknowledge support from<br /> the Simons Foundation, <a href="https://info.arxiv.org/about/ourmembers.html">member institutions</a>, and all contributors. <a href="https://info.arxiv.org/about/donate.html">Donate</a></span></p></div> </div>  <div class="identity level is-marginless"> <div class="level-left"> <div class="level-item"> <a class="arxiv" href="https://arxiv.org/" aria-label="arxiv-logo"> <img src="https://static.arxiv.org/static/base/1.0.0a5/images/arxiv-logo-one-color-white.svg" aria-label="logo" alt="arxiv logo" width="85" style="width:85px;"/> </a> </div> </div> <div class="search-block level-right"> <form class="level-item mini-search" method="GET" action="https://arxiv.org/search"> <div class="field has-addons"> <div class="control"> <input class="input is-small" type="text" name="query" placeholder="Search..." aria-label="Search term or terms" /> <p class="help"><a href="https://info.arxiv.org/help">Help</a> | <a href="https://arxiv.org/search/advanced">Advanced Search</a></p> </div> <div class="control"> <div class="select is-small"> <select name="searchtype" aria-label="Field to search"> <option value="all" selected="selected">All fields</option> <option value="title">Title</option> <option value="author">Author</option> <option value="abstract">Abstract</option> <option value="comments">Comments</option> <option value="journal_ref">Journal reference</option> <option value="acm_class">ACM classification</option> <option value="msc_class">MSC classification</option> <option value="report_num">Report number</option> <option value="paper_id">arXiv identifier</option> <option value="doi">DOI</option> <option value="orcid">ORCID</option> <option value="author_id">arXiv author ID</option> <option value="help">Help pages</option> <option value="full_text">Full text</option> </select> </div> </div> <input type="hidden" name="source" value="header"> <button class="button is-small is-cul-darker">Search</button> </div> </form> </div> </div>  <div class="container"> <div class="user-tools is-size-7 has-text-right has-text-weight-bold" role="navigation" aria-label="User menu"> <a href="https://arxiv.org/login">Login</a> </div> </div> </header> <main class="container" id="main-container"> <div class="level is-marginless"> <div class="level-left"> <h1 class="title is-clearfix"> Showing 1–50 of 553 results for author: <span class="mathjax">Yu, P S</span> </h1> </div> <div class="level-right is-hidden-mobile">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> <div class="content"> <form method="GET" action="/search/cs" aria-role="search"> Searching in archive <strong>cs</strong>. <a href="/search/?searchtype=author&query=Yu%2C+P+S">Search in all archives.</a> <div class="field has-addons-tablet"> <div class="control is-expanded"> <label for="query" class="hidden-label">Search term or terms</label> <input class="input is-medium" id="query" name="query" placeholder="Search term..." type="text" value="Yu, P S"> </div> <div class="select control is-medium"> <label class="is-hidden" for="searchtype">Field</label> <select class="is-medium" id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> </div> <div class="control"> <button class="button is-link is-medium">Search</button> </div> </div> <div class="field"> <div class="control is-size-7"> <label class="radio"> <input checked id="abstracts-0" name="abstracts" type="radio" value="show"> Show abstracts </label> <label class="radio"> <input id="abstracts-1" name="abstracts" type="radio" value="hide"> Hide abstracts </label> </div> </div> <div class="is-clearfix" style="height: 2.5em"> <div class="is-pulled-right"> <a href="/search/advanced?terms-0-term=Yu%2C+P+S&terms-0-field=author&size=50&order=-announced_date_first">Advanced Search</a> </div> </div> <input type="hidden" name="order" value="-announced_date_first"> <input type="hidden" name="size" value="50"> </form> <div class="level breathe-horizontal"> <div class="level-left"> <form method="GET" action="/search/"> <div style="display: none;"> <select id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> <input id="query" name="query" type="text" value="Yu, P S"> <ul id="abstracts"><li><input checked id="abstracts-0" name="abstracts" type="radio" value="show"> <label for="abstracts-0">Show abstracts</label></li><li><input id="abstracts-1" name="abstracts" type="radio" value="hide"> <label for="abstracts-1">Hide abstracts</label></li></ul> </div> <div class="box field is-grouped is-grouped-multiline level-item"> <div class="control"> <span class="select is-small"> <select id="size" name="size"><option value="25">25</option><option selected value="50">50</option><option value="100">100</option><option value="200">200</option></select> </span> <label for="size">results per page</label>. </div> <div class="control"> <label for="order">Sort results by</label> <span class="select is-small"> <select id="order" name="order"><option selected value="-announced_date_first">Announcement date (newest first)</option><option value="announced_date_first">Announcement date (oldest first)</option><option value="-submitted_date">Submission date (newest first)</option><option value="submitted_date">Submission date (oldest first)</option><option value="">Relevance</option></select> </span> </div> <div class="control"> <button class="button is-small is-link">Go</button> </div> </div> </form> </div> </div> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Yu%2C+P+S&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Yu%2C+P+S&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Yu%2C+P+S&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Yu%2C+P+S&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Yu%2C+P+S&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Yu%2C+P+S&start=200" class="pagination-link " aria-label="Page 5" aria-current="page">5 </a> </li> <li><span class="pagination-ellipsis">…</span></li> </ul> </nav> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.14296">arXiv:2502.14296</a> <span> [<a href="https://arxiv.org/pdf/2502.14296">pdf</a>, <a href="https://arxiv.org/format/2502.14296">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> </div> </div> <p class="title is-5 mathjax"> On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Huang%2C+Y">Yue Huang</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+C">Chujie Gao</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+S">Siyuan Wu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+H">Haoran Wang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+X">Xiangqi Wang</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Y">Yujun Zhou</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yanbo Wang</a>, <a href="/search/cs?searchtype=author&query=Ye%2C+J">Jiayi Ye</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+J">Jiawen Shi</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Q">Qihui Zhang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yuan Li</a>, <a href="/search/cs?searchtype=author&query=Bao%2C+H">Han Bao</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zhaoyi Liu</a>, <a href="/search/cs?searchtype=author&query=Guan%2C+T">Tianrui Guan</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+D">Dongping Chen</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+R">Ruoxi Chen</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+K">Kehan Guo</a>, <a href="/search/cs?searchtype=author&query=Zou%2C+A">Andy Zou</a>, <a href="/search/cs?searchtype=author&query=Kuen-Yew%2C+B+H">Bryan Hooi Kuen-Yew</a>, <a href="/search/cs?searchtype=author&query=Xiong%2C+C">Caiming Xiong</a>, <a href="/search/cs?searchtype=author&query=Stengel-Eskin%2C+E">Elias Stengel-Eskin</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+H">Hongyang Zhang</a>, <a href="/search/cs?searchtype=author&query=Yin%2C+H">Hongzhi Yin</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+H">Huan Zhang</a>, <a href="/search/cs?searchtype=author&query=Yao%2C+H">Huaxiu Yao</a> , et al. (41 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="2502.14296v1-abstract-short" style="display: inline;"> Generative Foundation Models (GenFMs) have emerged as transformative tools. However, their widespread adoption raises critical concerns regarding trustworthiness across dimensions. This paper presents a comprehensive framework to address these challenges through three key contributions. First, we systematically review global AI governance laws and policies from governments and regulatory bodies, a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.14296v1-abstract-full').style.display = 'inline'; document.getElementById('2502.14296v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.14296v1-abstract-full" style="display: none;"> Generative Foundation Models (GenFMs) have emerged as transformative tools. However, their widespread adoption raises critical concerns regarding trustworthiness across dimensions. This paper presents a comprehensive framework to address these challenges through three key contributions. First, we systematically review global AI governance laws and policies from governments and regulatory bodies, as well as industry practices and standards. Based on this analysis, we propose a set of guiding principles for GenFMs, developed through extensive multidisciplinary collaboration that integrates technical, ethical, legal, and societal perspectives. Second, we introduce TrustGen, the first dynamic benchmarking platform designed to evaluate trustworthiness across multiple dimensions and model types, including text-to-image, large language, and vision-language models. TrustGen leverages modular components--metadata curation, test case generation, and contextual variation--to enable adaptive and iterative assessments, overcoming the limitations of static evaluation methods. Using TrustGen, we reveal significant progress in trustworthiness while identifying persistent challenges. Finally, we provide an in-depth discussion of the challenges and future directions for trustworthy GenFMs, which reveals the complex, evolving nature of trustworthiness, highlighting the nuanced trade-offs between utility and trustworthiness, and consideration for various downstream applications, identifying persistent challenges and providing a strategic roadmap for future research. This work establishes a holistic framework for advancing trustworthiness in GenAI, paving the way for safer and more responsible integration of GenFMs into critical applications. To facilitate advancement in the community, we release the toolkit for dynamic evaluation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.14296v1-abstract-full').style.display = 'none'; document.getElementById('2502.14296v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.11598">arXiv:2502.11598</a> <span> [<a href="https://arxiv.org/pdf/2502.11598">pdf</a>, <a href="https://arxiv.org/format/2502.11598">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"> Can LLM Watermarks Robustly Prevent Unauthorized Knowledge Distillation? </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pan%2C+L">Leyi Pan</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+A">Aiwei Liu</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+S">Shiyu Huang</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+Y">Yijian Lu</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+X">Xuming Hu</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+L">Lijie Wen</a>, <a href="/search/cs?searchtype=author&query=King%2C+I">Irwin King</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2502.11598v1-abstract-short" style="display: inline;"> The radioactive nature of Large Language Model (LLM) watermarking enables the detection of watermarks inherited by student models when trained on the outputs of watermarked teacher models, making it a promising tool for preventing unauthorized knowledge distillation. However, the robustness of watermark radioactivity against adversarial actors remains largely unexplored. In this paper, we investig… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11598v1-abstract-full').style.display = 'inline'; document.getElementById('2502.11598v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.11598v1-abstract-full" style="display: none;"> The radioactive nature of Large Language Model (LLM) watermarking enables the detection of watermarks inherited by student models when trained on the outputs of watermarked teacher models, making it a promising tool for preventing unauthorized knowledge distillation. However, the robustness of watermark radioactivity against adversarial actors remains largely unexplored. In this paper, we investigate whether student models can acquire the capabilities of teacher models through knowledge distillation while avoiding watermark inheritance. We propose two categories of watermark removal approaches: pre-distillation removal through untargeted and targeted training data paraphrasing (UP and TP), and post-distillation removal through inference-time watermark neutralization (WN). Extensive experiments across multiple model pairs, watermarking schemes and hyper-parameter settings demonstrate that both TP and WN thoroughly eliminate inherited watermarks, with WN achieving this while maintaining knowledge transfer efficiency and low computational overhead. Given the ongoing deployment of watermarking techniques in production LLMs, these findings emphasize the urgent need for more robust defense strategies. Our code is available at https://github.com/THU-BPM/Watermark-Radioactivity-Attack. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11598v1-abstract-full').style.display = 'none'; document.getElementById('2502.11598v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">22 pages, 12 figures, 13 tables</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68T50 <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.2.7 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.10454">arXiv:2502.10454</a> <span> [<a href="https://arxiv.org/pdf/2502.10454">pdf</a>, <a href="https://arxiv.org/format/2502.10454">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"> One Example Shown, Many Concepts Known! Counterexample-Driven Conceptual Reasoning in Mathematical LLMs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yinghui Li</a>, <a href="/search/cs?searchtype=author&query=Kuang%2C+J">Jiayi Kuang</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+H">Haojing Huang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Zhikun Xu</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+X">Xinnian Liang</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+Y">Yi Yu</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+W">Wenlian Lu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yangning Li</a>, <a href="/search/cs?searchtype=author&query=Tan%2C+X">Xiaoyu Tan</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+C">Chao Qu</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+Y">Ying Shen</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+H">Hai-Tao Zheng</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2502.10454v1-abstract-short" style="display: inline;"> Leveraging mathematical Large Language Models (LLMs) for proof generation is a fundamental topic in LLMs research. We argue that the ability of current LLMs to prove statements largely depends on whether they have encountered the relevant proof process during training. This reliance limits their deeper understanding of mathematical theorems and related concepts. Inspired by the pedagogical method… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.10454v1-abstract-full').style.display = 'inline'; document.getElementById('2502.10454v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.10454v1-abstract-full" style="display: none;"> Leveraging mathematical Large Language Models (LLMs) for proof generation is a fundamental topic in LLMs research. We argue that the ability of current LLMs to prove statements largely depends on whether they have encountered the relevant proof process during training. This reliance limits their deeper understanding of mathematical theorems and related concepts. Inspired by the pedagogical method of "proof by counterexamples" commonly used in human mathematics education, our work aims to enhance LLMs' ability to conduct mathematical reasoning and proof through counterexamples. Specifically, we manually create a high-quality, university-level mathematical benchmark, CounterMATH, which requires LLMs to prove mathematical statements by providing counterexamples, thereby assessing their grasp of mathematical concepts. Additionally, we develop a data engineering framework to automatically obtain training data for further model improvement. Extensive experiments and detailed analyses demonstrate that CounterMATH is challenging, indicating that LLMs, such as OpenAI o1, have insufficient counterexample-driven proof capabilities. Moreover, our exploration into model training reveals that strengthening LLMs' counterexample-driven conceptual reasoning abilities is crucial for improving their overall mathematical capabilities. We believe that our work offers new perspectives on the community of mathematical LLMs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.10454v1-abstract-full').style.display = 'none'; document.getElementById('2502.10454v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.09335">arXiv:2502.09335</a> <span> [<a href="https://arxiv.org/pdf/2502.09335">pdf</a>, <a href="https://arxiv.org/format/2502.09335">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"> Graph Diffusion Network for Drug-Gene Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+J">Jiayang Wu</a>, <a href="/search/cs?searchtype=author&query=Gan%2C+W">Wensheng Gan</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2502.09335v1-abstract-short" style="display: inline;"> Predicting drug-gene associations is crucial for drug development and disease treatment. While graph neural networks (GNN) have shown effectiveness in this task, they face challenges with data sparsity and efficient contrastive learning implementation. We introduce a graph diffusion network for drug-gene prediction (GDNDGP), a framework that addresses these limitations through two key innovations.… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.09335v1-abstract-full').style.display = 'inline'; document.getElementById('2502.09335v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.09335v1-abstract-full" style="display: none;"> Predicting drug-gene associations is crucial for drug development and disease treatment. While graph neural networks (GNN) have shown effectiveness in this task, they face challenges with data sparsity and efficient contrastive learning implementation. We introduce a graph diffusion network for drug-gene prediction (GDNDGP), a framework that addresses these limitations through two key innovations. First, it employs meta-path-based homogeneous graph learning to capture drug-drug and gene-gene relationships, ensuring similar entities share embedding spaces. Second, it incorporates a parallel diffusion network that generates hard negative samples during training, eliminating the need for exhaustive negative sample retrieval. Our model achieves superior performance on the DGIdb 4.0 dataset and demonstrates strong generalization capability on tripartite drug-gene-disease networks. Results show significant improvements over existing methods in drug-gene prediction tasks, particularly in handling complex heterogeneous relationships. The source code is publicly available at https://github.com/csjywu1/GDNDGP. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.09335v1-abstract-full').style.display = 'none'; document.getElementById('2502.09335v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">IEEE/ACM TCBB. 14 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/2502.07184">arXiv:2502.07184</a> <span> [<a href="https://arxiv.org/pdf/2502.07184">pdf</a>, <a href="https://arxiv.org/format/2502.07184">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Refine Knowledge of Large Language Models via Adaptive Contrastive Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yinghui Li</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+H">Haojing Huang</a>, <a href="/search/cs?searchtype=author&query=Kuang%2C+J">Jiayi Kuang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yangning Li</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+S">Shu-Yu Guo</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+C">Chao Qu</a>, <a href="/search/cs?searchtype=author&query=Tan%2C+X">Xiaoyu Tan</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+H">Hai-Tao Zheng</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+Y">Ying Shen</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2502.07184v1-abstract-short" style="display: inline;"> How to alleviate the hallucinations of Large Language Models (LLMs) has always been the fundamental goal pursued by the LLMs research community. Looking through numerous hallucination-related studies, a mainstream category of methods is to reduce hallucinations by optimizing the knowledge representation of LLMs to change their output. Considering that the core focus of these works is the knowledge… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.07184v1-abstract-full').style.display = 'inline'; document.getElementById('2502.07184v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.07184v1-abstract-full" style="display: none;"> How to alleviate the hallucinations of Large Language Models (LLMs) has always been the fundamental goal pursued by the LLMs research community. Looking through numerous hallucination-related studies, a mainstream category of methods is to reduce hallucinations by optimizing the knowledge representation of LLMs to change their output. Considering that the core focus of these works is the knowledge acquired by models, and knowledge has long been a central theme in human societal progress, we believe that the process of models refining knowledge can greatly benefit from the way humans learn. In our work, by imitating the human learning process, we design an Adaptive Contrastive Learning strategy. Our method flexibly constructs different positive and negative samples for contrastive learning based on LLMs' actual mastery of knowledge. This strategy helps LLMs consolidate the correct knowledge they already possess, deepen their understanding of the correct knowledge they have encountered but not fully grasped, forget the incorrect knowledge they previously learned, and honestly acknowledge the knowledge they lack. Extensive experiments and detailed analyses on widely used datasets demonstrate the effectiveness of our method. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.07184v1-abstract-full').style.display = 'none'; document.getElementById('2502.07184v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to ICLR 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.06556">arXiv:2502.06556</a> <span> [<a href="https://arxiv.org/pdf/2502.06556">pdf</a>, <a href="https://arxiv.org/format/2502.06556">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</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"> ProjectTest: A Project-level LLM Unit Test Generation Benchmark and Impact of Error Fixing Mechanisms </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yibo Wang</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+C">Congying Xia</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+W">Wenting Zhao</a>, <a href="/search/cs?searchtype=author&query=Du%2C+J">Jiangshu Du</a>, <a href="/search/cs?searchtype=author&query=Miao%2C+C">Chunyu Miao</a>, <a href="/search/cs?searchtype=author&query=Deng%2C+Z">Zhongfen Deng</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. Yu</a>, <a href="/search/cs?searchtype=author&query=Xing%2C+C">Chen Xing</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="2502.06556v4-abstract-short" style="display: inline;"> Unit test generation has become a promising and important use case of LLMs. However, existing evaluation benchmarks for assessing LLM unit test generation capabilities focus on function- or class-level code rather than more practical and challenging project-level codebases. To address such limitation, we propose ProjectTest, a project-level benchmark for unit test generation covering Python, Java,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.06556v4-abstract-full').style.display = 'inline'; document.getElementById('2502.06556v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.06556v4-abstract-full" style="display: none;"> Unit test generation has become a promising and important use case of LLMs. However, existing evaluation benchmarks for assessing LLM unit test generation capabilities focus on function- or class-level code rather than more practical and challenging project-level codebases. To address such limitation, we propose ProjectTest, a project-level benchmark for unit test generation covering Python, Java, and JavaScript. ProjectTest features 20 moderate-sized and high-quality projects per language. We evaluate nine frontier LLMs on ProjectTest and the results show that all frontier LLMs tested exhibit moderate performance on ProjectTest on Python and Java, highlighting the difficulty of ProjectTest. We also conduct a thorough error analysis, which shows that even frontier LLMs, such as Claude-3.5-Sonnet, have significant basic yet critical errors, including compilation and cascade errors. Motivated by this observation, we further evaluate all frontier LLMs under manual error-fixing and self-error-fixing scenarios to assess their potential when equipped with error-fixing mechanisms. Our code and dataset is available at \href{https://github.com/YiboWANG214/ProjectTest}{ProjectTest}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.06556v4-abstract-full').style.display = 'none'; document.getElementById('2502.06556v4-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 10 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.05467">arXiv:2502.05467</a> <span> [<a href="https://arxiv.org/pdf/2502.05467">pdf</a>, <a href="https://arxiv.org/format/2502.05467">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Position: LLMs Can be Good Tutors in Foreign Language Education </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ye%2C+J">Jingheng Ye</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Shen Wang</a>, <a href="/search/cs?searchtype=author&query=Zou%2C+D">Deqing Zou</a>, <a href="/search/cs?searchtype=author&query=Yan%2C+Y">Yibo Yan</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+K">Kun Wang</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+H">Hai-Tao Zheng</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Zenglin Xu</a>, <a href="/search/cs?searchtype=author&query=King%2C+I">Irwin King</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. Yu</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+Q">Qingsong Wen</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="2502.05467v1-abstract-short" style="display: inline;"> While recent efforts have begun integrating large language models (LLMs) into foreign language education (FLE), they often rely on traditional approaches to learning tasks without fully embracing educational methodologies, thus lacking adaptability to language learning. To address this gap, we argue that LLMs have the potential to serve as effective tutors in FLE. Specifically, LLMs can play three… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.05467v1-abstract-full').style.display = 'inline'; document.getElementById('2502.05467v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.05467v1-abstract-full" style="display: none;"> While recent efforts have begun integrating large language models (LLMs) into foreign language education (FLE), they often rely on traditional approaches to learning tasks without fully embracing educational methodologies, thus lacking adaptability to language learning. To address this gap, we argue that LLMs have the potential to serve as effective tutors in FLE. Specifically, LLMs can play three critical roles: (1) as data enhancers, improving the creation of learning materials or serving as student simulations; (2) as task predictors, serving as learner assessment or optimizing learning pathway; and (3) as agents, enabling personalized and inclusive education. We encourage interdisciplinary research to explore these roles, fostering innovation while addressing challenges and risks, ultimately advancing FLE through the thoughtful integration of LLMs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.05467v1-abstract-full').style.display = 'none'; document.getElementById('2502.05467v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">18 pages, 4 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.03236">arXiv:2502.03236</a> <span> [<a href="https://arxiv.org/pdf/2502.03236">pdf</a>, <a href="https://arxiv.org/format/2502.03236">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Pioneer: Physics-informed Riemannian Graph ODE for Entropy-increasing Dynamics </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sun%2C+L">Li Sun</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Ziheng Zhang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zixi Wang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yujie Wang</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+Q">Qiqi Wan</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Hao Li</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+H">Hao Peng</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2502.03236v1-abstract-short" style="display: inline;"> Dynamic interacting system modeling is important for understanding and simulating real world systems. The system is typically described as a graph, where multiple objects dynamically interact with each other and evolve over time. In recent years, graph Ordinary Differential Equations (ODE) receive increasing research attentions. While achieving encouraging results, existing solutions prioritize th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.03236v1-abstract-full').style.display = 'inline'; document.getElementById('2502.03236v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.03236v1-abstract-full" style="display: none;"> Dynamic interacting system modeling is important for understanding and simulating real world systems. The system is typically described as a graph, where multiple objects dynamically interact with each other and evolve over time. In recent years, graph Ordinary Differential Equations (ODE) receive increasing research attentions. While achieving encouraging results, existing solutions prioritize the traditional Euclidean space, and neglect the intrinsic geometry of the system and physics laws, e.g., the principle of entropy increasing. The limitations above motivate us to rethink the system dynamics from a fresh perspective of Riemannian geometry, and pose a more realistic problem of physics-informed dynamic system modeling, considering the underlying geometry and physics law for the first time. In this paper, we present a novel physics-informed Riemannian graph ODE for a wide range of entropy-increasing dynamic systems (termed as Pioneer). In particular, we formulate a differential system on the Riemannian manifold, where a manifold-valued graph ODE is governed by the proposed constrained Ricci flow, and a manifold preserving Gyro-transform aware of system geometry. Theoretically, we report the provable entropy non-decreasing of our formulation, obeying the physics laws. Empirical results show the superiority of Pioneer on real datasets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.03236v1-abstract-full').style.display = 'none'; document.getElementById('2502.03236v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by AAAI25</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.02871">arXiv:2502.02871</a> <span> [<a href="https://arxiv.org/pdf/2502.02871">pdf</a>, <a href="https://arxiv.org/format/2502.02871">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yan%2C+Y">Yibo Yan</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Shen Wang</a>, <a href="/search/cs?searchtype=author&query=Huo%2C+J">Jiahao Huo</a>, <a href="/search/cs?searchtype=author&query=Ye%2C+J">Jingheng Ye</a>, <a href="/search/cs?searchtype=author&query=Chu%2C+Z">Zhendong Chu</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+X">Xuming Hu</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. Yu</a>, <a href="/search/cs?searchtype=author&query=Gomes%2C+C">Carla Gomes</a>, <a href="/search/cs?searchtype=author&query=Selman%2C+B">Bart Selman</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+Q">Qingsong Wen</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="2502.02871v1-abstract-short" style="display: inline;"> Scientific reasoning, the process through which humans apply logic, evidence, and critical thinking to explore and interpret scientific phenomena, is essential in advancing knowledge reasoning across diverse fields. However, despite significant progress, current scientific reasoning models still struggle with generalization across domains and often fall short of multimodal perception. Multimodal L… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.02871v1-abstract-full').style.display = 'inline'; document.getElementById('2502.02871v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.02871v1-abstract-full" style="display: none;"> Scientific reasoning, the process through which humans apply logic, evidence, and critical thinking to explore and interpret scientific phenomena, is essential in advancing knowledge reasoning across diverse fields. However, despite significant progress, current scientific reasoning models still struggle with generalization across domains and often fall short of multimodal perception. Multimodal Large Language Models (MLLMs), which integrate text, images, and other modalities, present an exciting opportunity to overcome these limitations and enhance scientific reasoning. Therefore, this position paper argues that MLLMs can significantly advance scientific reasoning across disciplines such as mathematics, physics, chemistry, and biology. First, we propose a four-stage research roadmap of scientific reasoning capabilities, and highlight the current state of MLLM applications in scientific reasoning, noting their ability to integrate and reason over diverse data types. Second, we summarize the key challenges that remain obstacles to achieving MLLM's full potential. To address these challenges, we propose actionable insights and suggestions for the future. Overall, our work offers a novel perspective on MLLM integration with scientific reasoning, providing the LLM community with a valuable vision for achieving Artificial General Intelligence (AGI). <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.02871v1-abstract-full').style.display = 'none'; document.getElementById('2502.02871v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.16352">arXiv:2501.16352</a> <span> [<a href="https://arxiv.org/pdf/2501.16352">pdf</a>, <a href="https://arxiv.org/format/2501.16352">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"> Mixture of Experts (MoE): A Big Data Perspective </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gan%2C+W">Wensheng Gan</a>, <a href="/search/cs?searchtype=author&query=Ning%2C+Z">Zhenyao Ning</a>, <a href="/search/cs?searchtype=author&query=Qi%2C+Z">Zhenlian Qi</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2501.16352v1-abstract-short" style="display: inline;"> As the era of big data arrives, traditional artificial intelligence algorithms have difficulty processing the demands of massive and diverse data. Mixture of experts (MoE) has shown excellent performance and broad application prospects. This paper provides an in-depth review and analysis of the latest progress in this field from multiple perspectives, including the basic principles, algorithmic mo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.16352v1-abstract-full').style.display = 'inline'; document.getElementById('2501.16352v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.16352v1-abstract-full" style="display: none;"> As the era of big data arrives, traditional artificial intelligence algorithms have difficulty processing the demands of massive and diverse data. Mixture of experts (MoE) has shown excellent performance and broad application prospects. This paper provides an in-depth review and analysis of the latest progress in this field from multiple perspectives, including the basic principles, algorithmic models, key technical challenges, and application practices of MoE. First, we introduce the basic concept of MoE and its core idea and elaborate on its advantages over traditional single models. Then, we discuss the basic architecture of MoE and its main components, including the gating network, expert networks, and learning algorithms. Next, we review the applications of MoE in addressing key technical issues in big data. For each challenge, we provide specific MoE solutions and their innovations. Furthermore, we summarize the typical use cases of MoE in various application domains. This fully demonstrates the powerful capability of MoE in big data processing. We also analyze the advantages of MoE in big data environments. Finally, we explore the future development trends of MoE. We believe that MoE will become an important paradigm of artificial intelligence in the era of big data. In summary, this paper systematically elaborates on the principles, techniques, and applications of MoE in big data processing, providing theoretical and practical references to further promote the application of MoE in real scenarios. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.16352v1-abstract-full').style.display = 'none'; document.getElementById('2501.16352v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Preprint. 5 figures, 3 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.15130">arXiv:2501.15130</a> <span> [<a href="https://arxiv.org/pdf/2501.15130">pdf</a>, <a href="https://arxiv.org/format/2501.15130">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> </div> </div> <p class="title is-5 mathjax"> Community Detection in Large-Scale Complex Networks via Structural Entropy Game </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xian%2C+Y">Yantuan Xian</a>, <a href="/search/cs?searchtype=author&query=Li%2C+P">Pu Li</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+H">Hao Peng</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+Z">Zhengtao Yu</a>, <a href="/search/cs?searchtype=author&query=Xiang%2C+Y">Yan Xiang</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2501.15130v1-abstract-short" style="display: inline;"> Community detection is a critical task in graph theory, social network analysis, and bioinformatics, where communities are defined as clusters of densely interconnected nodes. However, detecting communities in large-scale networks with millions of nodes and billions of edges remains challenging due to the inefficiency and unreliability of existing methods. Moreover, many current approaches are lim… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.15130v1-abstract-full').style.display = 'inline'; document.getElementById('2501.15130v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.15130v1-abstract-full" style="display: none;"> Community detection is a critical task in graph theory, social network analysis, and bioinformatics, where communities are defined as clusters of densely interconnected nodes. However, detecting communities in large-scale networks with millions of nodes and billions of edges remains challenging due to the inefficiency and unreliability of existing methods. Moreover, many current approaches are limited to specific graph types, such as unweighted or undirected graphs, reducing their broader applicability. To address these issues, we propose a novel heuristic community detection algorithm, termed CoDeSEG, which identifies communities by minimizing the two-dimensional (2D) structural entropy of the network within a potential game framework. In the game, nodes decide to stay in current community or move to another based on a strategy that maximizes the 2D structural entropy utility function. Additionally, we introduce a structural entropy-based node overlapping heuristic for detecting overlapping communities, with a near-linear time complexity.Experimental results on real-world networks demonstrate that CoDeSEG is the fastest method available and achieves state-of-the-art performance in overlapping normalized mutual information (ONMI) and F1 score. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.15130v1-abstract-full').style.display = 'none'; document.getElementById('2501.15130v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <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 The Web Conference 2025 (WWW2025)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.13908">arXiv:2501.13908</a> <span> [<a href="https://arxiv.org/pdf/2501.13908">pdf</a>, <a href="https://arxiv.org/format/2501.13908">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"> Graph Neural Controlled Differential Equations For Collaborative Filtering </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xu%2C+K">Ke Xu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+W">Weizhi Zhang</a>, <a href="/search/cs?searchtype=author&query=Song%2C+Z">Zihe Song</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Y">Yuanjie Zhu</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2501.13908v1-abstract-short" style="display: inline;"> Graph Convolution Networks (GCNs) are widely considered state-of-the-art for recommendation systems. Several studies in the field of recommendation systems have attempted to apply collaborative filtering (CF) into the Neural ODE framework. These studies follow the same idea as LightGCN, which removes the weight matrix or with a discrete weight matrix. However, we argue that weight control is criti… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.13908v1-abstract-full').style.display = 'inline'; document.getElementById('2501.13908v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.13908v1-abstract-full" style="display: none;"> Graph Convolution Networks (GCNs) are widely considered state-of-the-art for recommendation systems. Several studies in the field of recommendation systems have attempted to apply collaborative filtering (CF) into the Neural ODE framework. These studies follow the same idea as LightGCN, which removes the weight matrix or with a discrete weight matrix. However, we argue that weight control is critical for neural ODE-based methods. The importance of weight in creating tailored graph convolution for each node is crucial, and employing a fixed/discrete weight means it cannot adjust over time within the ODE function. This rigidity in the graph convolution reduces its adaptability, consequently hindering the performance of recommendations. In this study, to create an optimal control for Neural ODE-based recommendation, we introduce a new method called Graph Neural Controlled Differential Equations for Collaborative Filtering (CDE-CF). Our method improves the performance of the Graph ODE-based method by incorporating weight control in a continuous manner. To evaluate our approach, we conducted experiments on various datasets. The results show that our method surpasses competing baselines, including GCNs-based models and state-of-the-art Graph ODE-based methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.13908v1-abstract-full').style.display = 'none'; document.getElementById('2501.13908v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted in WWW 2025 short paper</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.12133">arXiv:2501.12133</a> <span> [<a href="https://arxiv.org/pdf/2501.12133">pdf</a>, <a href="https://arxiv.org/format/2501.12133">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Distributed Multi-Head Learning Systems for Power Consumption Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Syu%2C+J">Jia-Hao Syu</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+J+C">Jerry Chun-Wei Lin</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2501.12133v1-abstract-short" style="display: inline;"> As more and more automatic vehicles, power consumption prediction becomes a vital issue for task scheduling and energy management. Most research focuses on automatic vehicles in transportation, but few focus on automatic ground vehicles (AGVs) in smart factories, which face complex environments and generate large amounts of data. There is an inevitable trade-off between feature diversity and inter… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.12133v1-abstract-full').style.display = 'inline'; document.getElementById('2501.12133v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.12133v1-abstract-full" style="display: none;"> As more and more automatic vehicles, power consumption prediction becomes a vital issue for task scheduling and energy management. Most research focuses on automatic vehicles in transportation, but few focus on automatic ground vehicles (AGVs) in smart factories, which face complex environments and generate large amounts of data. There is an inevitable trade-off between feature diversity and interference. In this paper, we propose Distributed Multi-Head learning (DMH) systems for power consumption prediction in smart factories. Multi-head learning mechanisms are proposed in DMH to reduce noise interference and improve accuracy. Additionally, DMH systems are designed as distributed and split learning, reducing the client-to-server transmission cost, sharing knowledge without sharing local data and models, and enhancing the privacy and security levels. Experimental results show that the proposed DMH systems rank in the top-2 on most datasets and scenarios. DMH-E system reduces the error of the state-of-the-art systems by 14.5% to 24.0%. Effectiveness studies demonstrate the effectiveness of Pearson correlation-based feature engineering, and feature grouping with the proposed multi-head learning further enhances prediction performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.12133v1-abstract-full').style.display = 'none'; document.getElementById('2501.12133v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.07078">arXiv:2501.07078</a> <span> [<a href="https://arxiv.org/pdf/2501.07078">pdf</a>, <a href="https://arxiv.org/format/2501.07078">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="Databases">cs.DB</span> </div> </div> <p class="title is-5 mathjax"> ADKGD: Anomaly Detection in Knowledge Graphs with Dual-Channel Training </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+J">Jiayang Wu</a>, <a href="/search/cs?searchtype=author&query=Gan%2C+W">Wensheng Gan</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jiahao Zhang</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2501.07078v1-abstract-short" style="display: inline;"> In the current development of large language models (LLMs), it is important to ensure the accuracy and reliability of the underlying data sources. LLMs are critical for various applications, but they often suffer from hallucinations and inaccuracies due to knowledge gaps in the training data. Knowledge graphs (KGs), as a powerful structural tool, could serve as a vital external information source… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.07078v1-abstract-full').style.display = 'inline'; document.getElementById('2501.07078v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.07078v1-abstract-full" style="display: none;"> In the current development of large language models (LLMs), it is important to ensure the accuracy and reliability of the underlying data sources. LLMs are critical for various applications, but they often suffer from hallucinations and inaccuracies due to knowledge gaps in the training data. Knowledge graphs (KGs), as a powerful structural tool, could serve as a vital external information source to mitigate the aforementioned issues. By providing a structured and comprehensive understanding of real-world data, KGs enhance the performance and reliability of LLMs. However, it is common that errors exist in KGs while extracting triplets from unstructured data to construct KGs. This could lead to degraded performance in downstream tasks such as question-answering and recommender systems. Therefore, anomaly detection in KGs is essential to identify and correct these errors. This paper presents an anomaly detection algorithm in knowledge graphs with dual-channel learning (ADKGD). ADKGD leverages a dual-channel learning approach to enhance representation learning from both the entity-view and triplet-view perspectives. Furthermore, using a cross-layer approach, our framework integrates internal information aggregation and context information aggregation. We introduce a kullback-leibler (KL)-loss component to improve the accuracy of the scoring function between the dual channels. To evaluate ADKGD's performance, we conduct empirical studies on three real-world KGs: WN18RR, FB15K, and NELL-995. Experimental results demonstrate that ADKGD outperforms the state-of-the-art anomaly detection algorithms. The source code and datasets are publicly available at https://github.com/csjywu1/ADKGD. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.07078v1-abstract-full').style.display = 'none'; document.getElementById('2501.07078v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Preprint. 11 figures, 6 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.07069">arXiv:2501.07069</a> <span> [<a href="https://arxiv.org/pdf/2501.07069">pdf</a>, <a href="https://arxiv.org/format/2501.07069">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"> Hierarchical Superpixel Segmentation via Structural Information Theory </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xie%2C+M">Minhui Xie</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+H">Hao Peng</a>, <a href="/search/cs?searchtype=author&query=Li%2C+P">Pu Li</a>, <a href="/search/cs?searchtype=author&query=Zeng%2C+G">Guangjie Zeng</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Shuhai Wang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+J">Jia Wu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+P">Peng Li</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2501.07069v1-abstract-short" style="display: inline;"> Superpixel segmentation is a foundation for many higher-level computer vision tasks, such as image segmentation, object recognition, and scene understanding. Existing graph-based superpixel segmentation methods typically concentrate on the relationships between a given pixel and its directly adjacent pixels while overlooking the influence of non-adjacent pixels. These approaches do not fully lever… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.07069v1-abstract-full').style.display = 'inline'; document.getElementById('2501.07069v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.07069v1-abstract-full" style="display: none;"> Superpixel segmentation is a foundation for many higher-level computer vision tasks, such as image segmentation, object recognition, and scene understanding. Existing graph-based superpixel segmentation methods typically concentrate on the relationships between a given pixel and its directly adjacent pixels while overlooking the influence of non-adjacent pixels. These approaches do not fully leverage the global information in the graph, leading to suboptimal segmentation quality. To address this limitation, we present SIT-HSS, a hierarchical superpixel segmentation method based on structural information theory. Specifically, we first design a novel graph construction strategy that incrementally explores the pixel neighborhood to add edges based on 1-dimensional structural entropy (1D SE). This strategy maximizes the retention of graph information while avoiding an overly complex graph structure. Then, we design a new 2D SE-guided hierarchical graph partitioning method, which iteratively merges pixel clusters layer by layer to reduce the graph's 2D SE until a predefined segmentation scale is achieved. Experimental results on three benchmark datasets demonstrate that the SIT-HSS performs better than state-of-the-art unsupervised superpixel segmentation algorithms. The source code is available at \url{https://github.com/SELGroup/SIT-HSS}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.07069v1-abstract-full').style.display = 'none'; document.getElementById('2501.07069v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by SDM 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.06985">arXiv:2501.06985</a> <span> [<a href="https://arxiv.org/pdf/2501.06985">pdf</a>, <a href="https://arxiv.org/format/2501.06985">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="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Graph Contrastive Learning on Multi-label Classification for Recommendations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+J">Jiayang Wu</a>, <a href="/search/cs?searchtype=author&query=Gan%2C+W">Wensheng Gan</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+H">Huashen Lu</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2501.06985v1-abstract-short" style="display: inline;"> In business analysis, providing effective recommendations is essential for enhancing company profits. The utilization of graph-based structures, such as bipartite graphs, has gained popularity for their ability to analyze complex data relationships. Link prediction is crucial for recommending specific items to users. Traditional methods in this area often involve identifying patterns in the graph… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.06985v1-abstract-full').style.display = 'inline'; document.getElementById('2501.06985v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.06985v1-abstract-full" style="display: none;"> In business analysis, providing effective recommendations is essential for enhancing company profits. The utilization of graph-based structures, such as bipartite graphs, has gained popularity for their ability to analyze complex data relationships. Link prediction is crucial for recommending specific items to users. Traditional methods in this area often involve identifying patterns in the graph structure or using representational techniques like graph neural networks (GNNs). However, these approaches encounter difficulties as the volume of data increases. To address these challenges, we propose a model called Graph Contrastive Learning for Multi-label Classification (MCGCL). MCGCL leverages contrastive learning to enhance recommendation effectiveness. The model incorporates two training stages: a main task and a subtask. The main task is holistic user-item graph learning to capture user-item relationships. The homogeneous user-user (item-item) subgraph is constructed to capture user-user and item-item relationships in the subtask. We assessed the performance using real-world datasets from Amazon Reviews in multi-label classification tasks. Comparative experiments with state-of-the-art methods confirm the effectiveness of MCGCL, highlighting its potential for improving recommendation systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.06985v1-abstract-full').style.display = 'none'; document.getElementById('2501.06985v1-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> 12 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Preprint. 10 figures, 5 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.01945">arXiv:2501.01945</a> <span> [<a href="https://arxiv.org/pdf/2501.01945">pdf</a>, <a href="https://arxiv.org/format/2501.01945">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="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Cold-Start Recommendation towards the Era of Large Language Models (LLMs): A Comprehensive Survey and Roadmap </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+W">Weizhi Zhang</a>, <a href="/search/cs?searchtype=author&query=Bei%2C+Y">Yuanchen Bei</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+L">Liangwei Yang</a>, <a href="/search/cs?searchtype=author&query=Zou%2C+H+P">Henry Peng Zou</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+P">Peilin Zhou</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+A">Aiwei Liu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yinghui Li</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+H">Hao Chen</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jianling Wang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+F">Feiran Huang</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+S">Sheng Zhou</a>, <a href="/search/cs?searchtype=author&query=Bu%2C+J">Jiajun Bu</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+A">Allen Lin</a>, <a href="/search/cs?searchtype=author&query=Caverlee%2C+J">James Caverlee</a>, <a href="/search/cs?searchtype=author&query=Karray%2C+F">Fakhri Karray</a>, <a href="/search/cs?searchtype=author&query=King%2C+I">Irwin King</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2501.01945v2-abstract-short" style="display: inline;"> Cold-start problem is one of the long-standing challenges in recommender systems, focusing on accurately modeling new or interaction-limited users or items to provide better recommendations. Due to the diversification of internet platforms and the exponential growth of users and items, the importance of cold-start recommendation (CSR) is becoming increasingly evident. At the same time, large langu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.01945v2-abstract-full').style.display = 'inline'; document.getElementById('2501.01945v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.01945v2-abstract-full" style="display: none;"> Cold-start problem is one of the long-standing challenges in recommender systems, focusing on accurately modeling new or interaction-limited users or items to provide better recommendations. Due to the diversification of internet platforms and the exponential growth of users and items, the importance of cold-start recommendation (CSR) is becoming increasingly evident. At the same time, large language models (LLMs) have achieved tremendous success and possess strong capabilities in modeling user and item information, providing new potential for cold-start recommendations. However, the research community on CSR still lacks a comprehensive review and reflection in this field. Based on this, in this paper, we stand in the context of the era of large language models and provide a comprehensive review and discussion on the roadmap, related literature, and future directions of CSR. Specifically, we have conducted an exploration of the development path of how existing CSR utilizes information, from content features, graph relations, and domain information, to the world knowledge possessed by large language models, aiming to provide new insights for both the research and industrial communities on CSR. Related resources of cold-start recommendations are collected and continuously updated for the community in https://github.com/YuanchenBei/Awesome-Cold-Start-Recommendation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.01945v2-abstract-full').style.display = 'none'; document.getElementById('2501.01945v2-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 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 3 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.18760">arXiv:2412.18760</a> <span> [<a href="https://arxiv.org/pdf/2412.18760">pdf</a>, <a href="https://arxiv.org/format/2412.18760">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"> Data clustering: an essential technique in data science </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Dinh%2C+T">Tai Dinh</a>, <a href="/search/cs?searchtype=author&query=Hauchi%2C+W">Wong Hauchi</a>, <a href="/search/cs?searchtype=author&query=Lisik%2C+D">Daniil Lisik</a>, <a href="/search/cs?searchtype=author&query=Koren%2C+M">Michal Koren</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+D">Dat Tran</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. Yu</a>, <a href="/search/cs?searchtype=author&query=Torres-Sospedra%2C+J">Joaqu铆n Torres-Sospedra</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.18760v2-abstract-short" style="display: inline;"> This paper explores the critical role of data clustering in data science, emphasizing its methodologies, tools, and diverse applications. Traditional techniques, such as partitional and hierarchical clustering, are analyzed alongside advanced approaches such as data stream, density-based, graph-based, and model-based clustering for handling complex structured datasets. The paper highlights key pri… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.18760v2-abstract-full').style.display = 'inline'; document.getElementById('2412.18760v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.18760v2-abstract-full" style="display: none;"> This paper explores the critical role of data clustering in data science, emphasizing its methodologies, tools, and diverse applications. Traditional techniques, such as partitional and hierarchical clustering, are analyzed alongside advanced approaches such as data stream, density-based, graph-based, and model-based clustering for handling complex structured datasets. The paper highlights key principles underpinning clustering, outlines widely used tools and frameworks, introduces the workflow of clustering in data science, discusses challenges in practical implementation, and examines various applications of clustering. By focusing on these foundations and applications, the discussion underscores clustering's transformative potential. The paper concludes with insights into future research directions, emphasizing clustering's role in driving innovation and enabling data-driven decision-making. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.18760v2-abstract-full').style.display = 'none'; document.getElementById('2412.18760v2-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 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.18084">arXiv:2412.18084</a> <span> [<a href="https://arxiv.org/pdf/2412.18084">pdf</a>, <a href="https://arxiv.org/format/2412.18084">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"> Property Enhanced Instruction Tuning for Multi-task Molecule Generation with Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lin%2C+X">Xuan Lin</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+L">Long Chen</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yile Wang</a>, <a href="/search/cs?searchtype=author&query=Zeng%2C+X">Xiangxiang Zeng</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2412.18084v1-abstract-short" style="display: inline;"> Large language models (LLMs) are widely applied in various natural language processing tasks such as question answering and machine translation. However, due to the lack of labeled data and the difficulty of manual annotation for biochemical properties, the performance for molecule generation tasks is still limited, especially for tasks involving multi-properties constraints. In this work, we pres… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.18084v1-abstract-full').style.display = 'inline'; document.getElementById('2412.18084v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.18084v1-abstract-full" style="display: none;"> Large language models (LLMs) are widely applied in various natural language processing tasks such as question answering and machine translation. However, due to the lack of labeled data and the difficulty of manual annotation for biochemical properties, the performance for molecule generation tasks is still limited, especially for tasks involving multi-properties constraints. In this work, we present a two-step framework PEIT (Property Enhanced Instruction Tuning) to improve LLMs for molecular-related tasks. In the first step, we use textual descriptions, SMILES, and biochemical properties as multimodal inputs to pre-train a model called PEIT-GEN, by aligning multi-modal representations to synthesize instruction data. In the second step, we fine-tune existing open-source LLMs with the synthesized data, the resulting PEIT-LLM can handle molecule captioning, text-based molecule generation, molecular property prediction, and our newly proposed multi-constraint molecule generation tasks. Experimental results show that our pre-trained PEIT-GEN outperforms MolT5 and BioT5 in molecule captioning, demonstrating modalities align well between textual descriptions, structures, and biochemical properties. Furthermore, PEIT-LLM shows promising improvements in multi-task molecule generation, proving the scalability of the PEIT framework for various molecular tasks. We release the code, constructed instruction data, and model checkpoints in https://github.com/chenlong164/PEIT. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.18084v1-abstract-full').style.display = 'none'; document.getElementById('2412.18084v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.13472">arXiv:2412.13472</a> <span> [<a href="https://arxiv.org/pdf/2412.13472">pdf</a>, <a href="https://arxiv.org/format/2412.13472">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="Digital Libraries">cs.DL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> </div> </div> <p class="title is-5 mathjax"> SocialED: A Python Library for Social Event Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+K">Kun Zhang</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+X">Xiaoyan Yu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+P">Pu Li</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+H">Hao Peng</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2412.13472v1-abstract-short" style="display: inline;"> SocialED is a comprehensive, open-source Python library designed to support social event detection (SED) tasks, integrating 19 detection algorithms and 14 diverse datasets. It provides a unified API with detailed documentation, offering researchers and practitioners a complete solution for event detection in social media. The library is designed with modularity in mind, allowing users to easily ad… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.13472v1-abstract-full').style.display = 'inline'; document.getElementById('2412.13472v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.13472v1-abstract-full" style="display: none;"> SocialED is a comprehensive, open-source Python library designed to support social event detection (SED) tasks, integrating 19 detection algorithms and 14 diverse datasets. It provides a unified API with detailed documentation, offering researchers and practitioners a complete solution for event detection in social media. The library is designed with modularity in mind, allowing users to easily adapt and extend components for various use cases. SocialED supports a wide range of preprocessing techniques, such as graph construction and tokenization, and includes standardized interfaces for training models and making predictions. By integrating popular deep learning frameworks, SocialED ensures high efficiency and scalability across both CPU and GPU environments. The library is built adhering to high code quality standards, including unit testing, continuous integration, and code coverage, ensuring that SocialED delivers robust, maintainable software. SocialED is publicly available at \url{https://github.com/RingBDStack/SocialED} and can be installed via PyPI. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.13472v1-abstract-full').style.display = 'none'; document.getElementById('2412.13472v1-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 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 pages, 1 figure, Python library</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.10712">arXiv:2412.10712</a> <span> [<a href="https://arxiv.org/pdf/2412.10712">pdf</a>, <a href="https://arxiv.org/format/2412.10712">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"> Towards Effective, Efficient and Unsupervised Social Event Detection in the Hyperbolic Space </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yu%2C+X">Xiaoyan Yu</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+Y">Yifan Wei</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+S">Shuaishuai Zhou</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Z">Zhiwei Yang</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+L">Li Sun</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+H">Hao Peng</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+L">Liehuang Zhu</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2412.10712v1-abstract-short" style="display: inline;"> The vast, complex, and dynamic nature of social message data has posed challenges to social event detection (SED). Despite considerable effort, these challenges persist, often resulting in inadequately expressive message representations (ineffective) and prolonged learning durations (inefficient). In response to the challenges, this work introduces an unsupervised framework, HyperSED (Hyperbolic S… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.10712v1-abstract-full').style.display = 'inline'; document.getElementById('2412.10712v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.10712v1-abstract-full" style="display: none;"> The vast, complex, and dynamic nature of social message data has posed challenges to social event detection (SED). Despite considerable effort, these challenges persist, often resulting in inadequately expressive message representations (ineffective) and prolonged learning durations (inefficient). In response to the challenges, this work introduces an unsupervised framework, HyperSED (Hyperbolic SED). Specifically, the proposed framework first models social messages into semantic-based message anchors, and then leverages the structure of the anchor graph and the expressiveness of the hyperbolic space to acquire structure- and geometry-aware anchor representations. Finally, HyperSED builds the partitioning tree of the anchor message graph by incorporating differentiable structural information as the reflection of the detected events. Extensive experiments on public datasets demonstrate HyperSED's competitive performance, along with a substantial improvement in efficiency compared to the current state-of-the-art unsupervised paradigm. Statistically, HyperSED boosts incremental SED by an average of 2%, 2%, and 25% in NMI, AMI, and ARI, respectively; enhancing efficiency by up to 37.41 times and at least 12.10 times, illustrating the advancement of the proposed framework. Our code is publicly available at https://github.com/XiaoyanWork/HyperSED. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.10712v1-abstract-full').style.display = 'none'; document.getElementById('2412.10712v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to AAAI 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.08841">arXiv:2412.08841</a> <span> [<a href="https://arxiv.org/pdf/2412.08841">pdf</a>, <a href="https://arxiv.org/format/2412.08841">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"> Structural Entropy Guided Probabilistic Coding </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Huang%2C+X">Xiang Huang</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+H">Hao Peng</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+L">Li Sun</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+H">Hui Lin</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+C">Chunyang Liu</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+J">Jiang Cao</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2412.08841v2-abstract-short" style="display: inline;"> Probabilistic embeddings have several advantages over deterministic embeddings as they map each data point to a distribution, which better describes the uncertainty and complexity of data. Many works focus on adjusting the distribution constraint under the Information Bottleneck (IB) principle to enhance representation learning. However, these proposed regularization terms only consider the constr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.08841v2-abstract-full').style.display = 'inline'; document.getElementById('2412.08841v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.08841v2-abstract-full" style="display: none;"> Probabilistic embeddings have several advantages over deterministic embeddings as they map each data point to a distribution, which better describes the uncertainty and complexity of data. Many works focus on adjusting the distribution constraint under the Information Bottleneck (IB) principle to enhance representation learning. However, these proposed regularization terms only consider the constraint of each latent variable, omitting the structural information between latent variables. In this paper, we propose a novel structural entropy-guided probabilistic coding model, named SEPC. Specifically, we incorporate the relationship between latent variables into the optimization by proposing a structural entropy regularization loss. Besides, as traditional structural information theory is not well-suited for regression tasks, we propose a probabilistic encoding tree, transferring regression tasks to classification tasks while diminishing the influence of the transformation. Experimental results across 12 natural language understanding tasks, including both classification and regression tasks, demonstrate the superior performance of SEPC compared to other state-of-the-art models in terms of effectiveness, generalization capability, and robustness to label noise. The codes and datasets are available at https://github.com/SELGroup/SEPC. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.08841v2-abstract-full').style.display = 'none'; document.getElementById('2412.08841v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 11 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">This paper is accepted by AAAI 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.06864">arXiv:2412.06864</a> <span> [<a href="https://arxiv.org/pdf/2412.06864">pdf</a>, <a href="https://arxiv.org/format/2412.06864">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Political-LLM: Large Language Models in Political Science </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+L">Lincan Li</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Jiaqi Li</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Catherine Chen</a>, <a href="/search/cs?searchtype=author&query=Gui%2C+F">Fred Gui</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+H">Hongjia Yang</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+C">Chenxiao Yu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zhengguang Wang</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+J">Jianing Cai</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J+A">Junlong Aaron Zhou</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+B">Bolin Shen</a>, <a href="/search/cs?searchtype=author&query=Qian%2C+A">Alex Qian</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+W">Weixin Chen</a>, <a href="/search/cs?searchtype=author&query=Xue%2C+Z">Zhongkai Xue</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+L">Lichao Sun</a>, <a href="/search/cs?searchtype=author&query=He%2C+L">Lifang He</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+H">Hanjie Chen</a>, <a href="/search/cs?searchtype=author&query=Ding%2C+K">Kaize Ding</a>, <a href="/search/cs?searchtype=author&query=Du%2C+Z">Zijian Du</a>, <a href="/search/cs?searchtype=author&query=Mu%2C+F">Fangzhou Mu</a>, <a href="/search/cs?searchtype=author&query=Pei%2C+J">Jiaxin Pei</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+J">Jieyu Zhao</a>, <a href="/search/cs?searchtype=author&query=Swayamdipta%2C+S">Swabha Swayamdipta</a>, <a href="/search/cs?searchtype=author&query=Neiswanger%2C+W">Willie Neiswanger</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+H">Hua Wei</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+X">Xiyang Hu</a> , et al. (22 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="2412.06864v1-abstract-short" style="display: inline;"> In recent years, large language models (LLMs) have been widely adopted in political science tasks such as election prediction, sentiment analysis, policy impact assessment, and misinformation detection. Meanwhile, the need to systematically understand how LLMs can further revolutionize the field also becomes urgent. In this work, we--a multidisciplinary team of researchers spanning computer scienc… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.06864v1-abstract-full').style.display = 'inline'; document.getElementById('2412.06864v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.06864v1-abstract-full" style="display: none;"> In recent years, large language models (LLMs) have been widely adopted in political science tasks such as election prediction, sentiment analysis, policy impact assessment, and misinformation detection. Meanwhile, the need to systematically understand how LLMs can further revolutionize the field also becomes urgent. In this work, we--a multidisciplinary team of researchers spanning computer science and political science--present the first principled framework termed Political-LLM to advance the comprehensive understanding of integrating LLMs into computational political science. Specifically, we first introduce a fundamental taxonomy classifying the existing explorations into two perspectives: political science and computational methodologies. In particular, from the political science perspective, we highlight the role of LLMs in automating predictive and generative tasks, simulating behavior dynamics, and improving causal inference through tools like counterfactual generation; from a computational perspective, we introduce advancements in data preparation, fine-tuning, and evaluation methods for LLMs that are tailored to political contexts. We identify key challenges and future directions, emphasizing the development of domain-specific datasets, addressing issues of bias and fairness, incorporating human expertise, and redefining evaluation criteria to align with the unique requirements of computational political science. Political-LLM seeks to serve as a guidebook for researchers to foster an informed, ethical, and impactful use of Artificial Intelligence in political science. Our online resource is available at: http://political-llm.org/. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.06864v1-abstract-full').style.display = 'none'; document.getElementById('2412.06864v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">54 Pages, 9 Figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.04276">arXiv:2412.04276</a> <span> [<a href="https://arxiv.org/pdf/2412.04276">pdf</a>, <a href="https://arxiv.org/format/2412.04276">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 class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1145/3701716.3715498">10.1145/3701716.3715498 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Graph-Sequential Alignment and Uniformity: Toward Enhanced Recommendation Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Cao%2C+Y">Yuwei Cao</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+L">Liangwei Yang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zhiwei Liu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yuqing Liu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+C">Chen Wang</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+Y">Yueqing Liang</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+H">Hao Peng</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2412.04276v2-abstract-short" style="display: inline;"> Graph-based and sequential methods are two popular recommendation paradigms, each excelling in its domain but lacking the ability to leverage signals from the other. To address this, we propose a novel method that integrates both approaches for enhanced performance. Our framework uses Graph Neural Network (GNN)-based and sequential recommenders as separate submodules while sharing a unified embedd… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.04276v2-abstract-full').style.display = 'inline'; document.getElementById('2412.04276v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.04276v2-abstract-full" style="display: none;"> Graph-based and sequential methods are two popular recommendation paradigms, each excelling in its domain but lacking the ability to leverage signals from the other. To address this, we propose a novel method that integrates both approaches for enhanced performance. Our framework uses Graph Neural Network (GNN)-based and sequential recommenders as separate submodules while sharing a unified embedding space optimized jointly. To enable positive knowledge transfer, we design a loss function that enforces alignment and uniformity both within and across submodules. Experiments on three real-world datasets demonstrate that the proposed method significantly outperforms using either approach alone and achieves state-of-the-art results. Our implementations are publicly available at https://github.com/YuweiCao-UIC/GSAU.git. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.04276v2-abstract-full').style.display = 'none'; document.getElementById('2412.04276v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to The Web Conference 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.01333">arXiv:2412.01333</a> <span> [<a href="https://arxiv.org/pdf/2412.01333">pdf</a>, <a href="https://arxiv.org/format/2412.01333">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> Can Large Language Models Serve as Evaluators for Code Summarization? </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yang Wu</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+Y">Yao Wan</a>, <a href="/search/cs?searchtype=author&query=Chu%2C+Z">Zhaoyang Chu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+W">Wenting Zhao</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Ye Liu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+H">Hongyu Zhang</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+X">Xuanhua Shi</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2412.01333v1-abstract-short" style="display: inline;"> Code summarization facilitates program comprehension and software maintenance by converting code snippets into natural-language descriptions. Over the years, numerous methods have been developed for this task, but a key challenge remains: effectively evaluating the quality of generated summaries. While human evaluation is effective for assessing code summary quality, it is labor-intensive and diff… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.01333v1-abstract-full').style.display = 'inline'; document.getElementById('2412.01333v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.01333v1-abstract-full" style="display: none;"> Code summarization facilitates program comprehension and software maintenance by converting code snippets into natural-language descriptions. Over the years, numerous methods have been developed for this task, but a key challenge remains: effectively evaluating the quality of generated summaries. While human evaluation is effective for assessing code summary quality, it is labor-intensive and difficult to scale. Commonly used automatic metrics, such as BLEU, ROUGE-L, METEOR, and BERTScore, often fail to align closely with human judgments. In this paper, we explore the potential of Large Language Models (LLMs) for evaluating code summarization. We propose CODERPE (Role-Player for Code Summarization Evaluation), a novel method that leverages role-player prompting to assess the quality of generated summaries. Specifically, we prompt an LLM agent to play diverse roles, such as code reviewer, code author, code editor, and system analyst. Each role evaluates the quality of code summaries across key dimensions, including coherence, consistency, fluency, and relevance. We further explore the robustness of LLMs as evaluators by employing various prompting strategies, including chain-of-thought reasoning, in-context learning, and tailored rating form designs. The results demonstrate that LLMs serve as effective evaluators for code summarization methods. Notably, our LLM-based evaluator, CODERPE , achieves an 81.59% Spearman correlation with human evaluations, outperforming the existing BERTScore metric by 17.27%. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.01333v1-abstract-full').style.display = 'none'; document.getElementById('2412.01333v1-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> 2 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.00984">arXiv:2412.00984</a> <span> [<a href="https://arxiv.org/pdf/2412.00984">pdf</a>, <a href="https://arxiv.org/format/2412.00984">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> </div> </div> <p class="title is-5 mathjax"> TGTOD: A Global Temporal Graph Transformer for Outlier Detection at Scale </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+K">Kay Liu</a>, <a href="/search/cs?searchtype=author&query=Ding%2C+J">Jiahao Ding</a>, <a href="/search/cs?searchtype=author&query=Torkamani%2C+M">MohamadAli Torkamani</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2412.00984v1-abstract-short" style="display: inline;"> While Transformers have revolutionized machine learning on various data, existing Transformers for temporal graphs face limitations in (1) restricted receptive fields, (2) overhead of subgraph extraction, and (3) suboptimal generalization capability beyond link prediction. In this paper, we rethink temporal graph Transformers and propose TGTOD, a novel end-to-end Temporal Graph Transformer for Out… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.00984v1-abstract-full').style.display = 'inline'; document.getElementById('2412.00984v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.00984v1-abstract-full" style="display: none;"> While Transformers have revolutionized machine learning on various data, existing Transformers for temporal graphs face limitations in (1) restricted receptive fields, (2) overhead of subgraph extraction, and (3) suboptimal generalization capability beyond link prediction. In this paper, we rethink temporal graph Transformers and propose TGTOD, a novel end-to-end Temporal Graph Transformer for Outlier Detection. TGTOD employs global attention to model both structural and temporal dependencies within temporal graphs. To tackle scalability, our approach divides large temporal graphs into spatiotemporal patches, which are then processed by a hierarchical Transformer architecture comprising Patch Transformer, Cluster Transformer, and Temporal Transformer. We evaluate TGTOD on three public datasets under two settings, comparing with a wide range of baselines. Our experimental results demonstrate the effectiveness of TGTOD, achieving AP improvement of 61% on Elliptic. Furthermore, our efficiency evaluation shows that TGTOD reduces training time by 44x compared to existing Transformers for temporal graphs. To foster reproducibility, we make our implementation publicly available at https://github.com/kayzliu/tgtod. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.00984v1-abstract-full').style.display = 'none'; document.getElementById('2412.00984v1-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 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Preprint. Under review. Code available at https://github.com/kayzliu/tgtod</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.00756">arXiv:2412.00756</a> <span> [<a href="https://arxiv.org/pdf/2412.00756">pdf</a>, <a href="https://arxiv.org/format/2412.00756">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"> Multi-View Incongruity Learning for Multimodal Sarcasm Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Guo%2C+D">Diandian Guo</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+C">Cong Cao</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+F">Fangfang Yuan</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yanbing Liu</a>, <a href="/search/cs?searchtype=author&query=Zeng%2C+G">Guangjie Zeng</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+X">Xiaoyan Yu</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+H">Hao Peng</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2412.00756v2-abstract-short" style="display: inline;"> Multimodal sarcasm detection (MSD) is essential for various downstream tasks. Existing MSD methods tend to rely on spurious correlations. These methods often mistakenly prioritize non-essential features yet still make correct predictions, demonstrating poor generalizability beyond training environments. Regarding this phenomenon, this paper undertakes several initiatives. Firstly, we identify two… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.00756v2-abstract-full').style.display = 'inline'; document.getElementById('2412.00756v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.00756v2-abstract-full" style="display: none;"> Multimodal sarcasm detection (MSD) is essential for various downstream tasks. Existing MSD methods tend to rely on spurious correlations. These methods often mistakenly prioritize non-essential features yet still make correct predictions, demonstrating poor generalizability beyond training environments. Regarding this phenomenon, this paper undertakes several initiatives. Firstly, we identify two primary causes that lead to the reliance of spurious correlations. Secondly, we address these challenges by proposing a novel method that integrate Multimodal Incongruities via Contrastive Learning (MICL) for multimodal sarcasm detection. Specifically, we first leverage incongruity to drive multi-view learning from three views: token-patch, entity-object, and sentiment. Then, we introduce extensive data augmentation to mitigate the biased learning of the textual modality. Additionally, we construct a test set, SPMSD, which consists potential spurious correlations to evaluate the the model's generalizability. Experimental results demonstrate the superiority of MICL on benchmark datasets, along with the analyses showcasing MICL's advancement in mitigating the effect of spurious correlation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.00756v2-abstract-full').style.display = 'none'; document.getElementById('2412.00756v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 1 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to COLING 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.13700">arXiv:2411.13700</a> <span> [<a href="https://arxiv.org/pdf/2411.13700">pdf</a>, <a href="https://arxiv.org/format/2411.13700">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> </div> </div> <p class="title is-5 mathjax"> A Collaborative Ensemble Framework for CTR Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xiaolong Liu</a>, <a href="/search/cs?searchtype=author&query=Zeng%2C+Z">Zhichen Zeng</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xiaoyi Liu</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+S">Siyang Yuan</a>, <a href="/search/cs?searchtype=author&query=Song%2C+W">Weinan Song</a>, <a href="/search/cs?searchtype=author&query=Hang%2C+M">Mengyue Hang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yiqun Liu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+C">Chaofei Yang</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+D">Donghyun Kim</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+W">Wen-Yen Chen</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+J">Jiyan Yang</a>, <a href="/search/cs?searchtype=author&query=Han%2C+Y">Yiping Han</a>, <a href="/search/cs?searchtype=author&query=Jin%2C+R">Rong Jin</a>, <a href="/search/cs?searchtype=author&query=Long%2C+B">Bo Long</a>, <a href="/search/cs?searchtype=author&query=Tong%2C+H">Hanghang Tong</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2411.13700v1-abstract-short" style="display: inline;"> Recent advances in foundation models have established scaling laws that enable the development of larger models to achieve enhanced performance, motivating extensive research into large-scale recommendation models. However, simply increasing the model size in recommendation systems, even with large amounts of data, does not always result in the expected performance improvements. In this paper, we… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13700v1-abstract-full').style.display = 'inline'; document.getElementById('2411.13700v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.13700v1-abstract-full" style="display: none;"> Recent advances in foundation models have established scaling laws that enable the development of larger models to achieve enhanced performance, motivating extensive research into large-scale recommendation models. However, simply increasing the model size in recommendation systems, even with large amounts of data, does not always result in the expected performance improvements. In this paper, we propose a novel framework, Collaborative Ensemble Training Network (CETNet), to leverage multiple distinct models, each with its own embedding table, to capture unique feature interaction patterns. Unlike naive model scaling, our approach emphasizes diversity and collaboration through collaborative learning, where models iteratively refine their predictions. To dynamically balance contributions from each model, we introduce a confidence-based fusion mechanism using general softmax, where model confidence is computed via negation entropy. This design ensures that more confident models have a greater influence on the final prediction while benefiting from the complementary strengths of other models. We validate our framework on three public datasets (AmazonElectronics, TaobaoAds, and KuaiVideo) as well as a large-scale industrial dataset from Meta, demonstrating its superior performance over individual models and state-of-the-art baselines. Additionally, we conduct further experiments on the Criteo and Avazu datasets to compare our method with the multi-embedding paradigm. Our results show that our framework achieves comparable or better performance with smaller embedding sizes, offering a scalable and efficient solution for CTR prediction tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13700v1-abstract-full').style.display = 'none'; document.getElementById('2411.13700v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.09852">arXiv:2411.09852</a> <span> [<a href="https://arxiv.org/pdf/2411.09852">pdf</a>, <a href="https://arxiv.org/format/2411.09852">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="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"> InterFormer: Towards Effective Heterogeneous Interaction Learning for Click-Through Rate Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zeng%2C+Z">Zhichen Zeng</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xiaolong Liu</a>, <a href="/search/cs?searchtype=author&query=Hang%2C+M">Mengyue Hang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xiaoyi Liu</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Q">Qinghai Zhou</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+C">Chaofei Yang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yiqun Liu</a>, <a href="/search/cs?searchtype=author&query=Ruan%2C+Y">Yichen Ruan</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+L">Laming Chen</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yuxin Chen</a>, <a href="/search/cs?searchtype=author&query=Hao%2C+Y">Yujia Hao</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+J">Jiaqi Xu</a>, <a href="/search/cs?searchtype=author&query=Nie%2C+J">Jade Nie</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xi Liu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Buyun Zhang</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+W">Wei Wen</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+S">Siyang Yuan</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+K">Kai Wang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+W">Wen-Yen Chen</a>, <a href="/search/cs?searchtype=author&query=Han%2C+Y">Yiping Han</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Huayu Li</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+C">Chunzhi Yang</a>, <a href="/search/cs?searchtype=author&query=Long%2C+B">Bo Long</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. Yu</a>, <a href="/search/cs?searchtype=author&query=Tong%2C+H">Hanghang Tong</a> , et al. (1 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="2411.09852v2-abstract-short" style="display: inline;"> Click-through rate (CTR) prediction, which predicts the probability of a user clicking an ad, is a fundamental task in recommender systems. The emergence of heterogeneous information, such as user profile and behavior sequences, depicts user interests from different aspects. A mutually beneficial integration of heterogeneous information is the cornerstone towards the success of CTR prediction. How… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09852v2-abstract-full').style.display = 'inline'; document.getElementById('2411.09852v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.09852v2-abstract-full" style="display: none;"> Click-through rate (CTR) prediction, which predicts the probability of a user clicking an ad, is a fundamental task in recommender systems. The emergence of heterogeneous information, such as user profile and behavior sequences, depicts user interests from different aspects. A mutually beneficial integration of heterogeneous information is the cornerstone towards the success of CTR prediction. However, most of the existing methods suffer from two fundamental limitations, including (1) insufficient inter-mode interaction due to the unidirectional information flow between modes, and (2) aggressive information aggregation caused by early summarization, resulting in excessive information loss. To address the above limitations, we propose a novel module named InterFormer to learn heterogeneous information interaction in an interleaving style. To achieve better interaction learning, InterFormer enables bidirectional information flow for mutually beneficial learning across different modes. To avoid aggressive information aggregation, we retain complete information in each data mode and use a separate bridging arch for effective information selection and summarization. Our proposed InterFormer achieves state-of-the-art performance on three public datasets and a large-scale industrial dataset. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09852v2-abstract-full').style.display = 'none'; document.getElementById('2411.09852v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 14 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10 pages, 6 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/2411.07691">arXiv:2411.07691</a> <span> [<a href="https://arxiv.org/pdf/2411.07691">pdf</a>, <a href="https://arxiv.org/format/2411.07691">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"> New Emerged Security and Privacy of Pre-trained Model: a Survey and Outlook </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+M">Meng Yang</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+T">Tianqing Zhu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+C">Chi Liu</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+W">WanLei Zhou</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+S">Shui Yu</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2411.07691v1-abstract-short" style="display: inline;"> Thanks to the explosive growth of data and the development of computational resources, it is possible to build pre-trained models that can achieve outstanding performance on various tasks, such as neural language processing, computer vision, and more. Despite their powerful capabilities, pre-trained models have also sparked attention to the emerging security challenges associated with their real-w… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07691v1-abstract-full').style.display = 'inline'; document.getElementById('2411.07691v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.07691v1-abstract-full" style="display: none;"> Thanks to the explosive growth of data and the development of computational resources, it is possible to build pre-trained models that can achieve outstanding performance on various tasks, such as neural language processing, computer vision, and more. Despite their powerful capabilities, pre-trained models have also sparked attention to the emerging security challenges associated with their real-world applications. Security and privacy issues, such as leaking privacy information and generating harmful responses, have seriously undermined users' confidence in these powerful models. Concerns are growing as model performance improves dramatically. Researchers are eager to explore the unique security and privacy issues that have emerged, their distinguishing factors, and how to defend against them. However, the current literature lacks a clear taxonomy of emerging attacks and defenses for pre-trained models, which hinders a high-level and comprehensive understanding of these questions. To fill the gap, we conduct a systematical survey on the security risks of pre-trained models, proposing a taxonomy of attack and defense methods based on the accessibility of pre-trained models' input and weights in various security test scenarios. This taxonomy categorizes attacks and defenses into No-Change, Input-Change, and Model-Change approaches. With the taxonomy analysis, we capture the unique security and privacy issues of pre-trained models, categorizing and summarizing existing security issues based on their characteristics. In addition, we offer a timely and comprehensive review of each category's strengths and limitations. Our survey concludes by highlighting potential new research opportunities in the security and privacy of pre-trained models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07691v1-abstract-full').style.display = 'none'; document.getElementById('2411.07691v1-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> 12 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.02937">arXiv:2411.02937</a> <span> [<a href="https://arxiv.org/pdf/2411.02937">pdf</a>, <a href="https://arxiv.org/format/2411.02937">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"> Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yangning Li</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yinghui Li</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+X">Xinyu Wang</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+Y">Yong Jiang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhen Zhang</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+X">Xinran Zheng</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+H">Hui Wang</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+H">Hai-Tao Zheng</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+P">Pengjun Xie</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. Yu</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+F">Fei Huang</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jingren 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="2411.02937v3-abstract-short" style="display: inline;"> Multimodal Retrieval Augmented Generation (mRAG) plays an important role in mitigating the "hallucination" issue inherent in multimodal large language models (MLLMs). Although promising, existing heuristic mRAGs typically predefined fixed retrieval processes, which causes two issues: (1) Non-adaptive Retrieval Queries. (2) Overloaded Retrieval Queries. However, these flaws cannot be adequately ref… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02937v3-abstract-full').style.display = 'inline'; document.getElementById('2411.02937v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.02937v3-abstract-full" style="display: none;"> Multimodal Retrieval Augmented Generation (mRAG) plays an important role in mitigating the "hallucination" issue inherent in multimodal large language models (MLLMs). Although promising, existing heuristic mRAGs typically predefined fixed retrieval processes, which causes two issues: (1) Non-adaptive Retrieval Queries. (2) Overloaded Retrieval Queries. However, these flaws cannot be adequately reflected by current knowledge-seeking visual question answering (VQA) datasets, since the most required knowledge can be readily obtained with a standard two-step retrieval. To bridge the dataset gap, we first construct Dyn-VQA dataset, consisting of three types of "dynamic" questions, which require complex knowledge retrieval strategies variable in query, tool, and time: (1) Questions with rapidly changing answers. (2) Questions requiring multi-modal knowledge. (3) Multi-hop questions. Experiments on Dyn-VQA reveal that existing heuristic mRAGs struggle to provide sufficient and precisely relevant knowledge for dynamic questions due to their rigid retrieval processes. Hence, we further propose the first self-adaptive planning agent for multimodal retrieval, OmniSearch. The underlying idea is to emulate the human behavior in question solution which dynamically decomposes complex multimodal questions into sub-question chains with retrieval action. Extensive experiments prove the effectiveness of our OmniSearch, also provide direction for advancing mRAG. The code and dataset will be open-sourced at https://github.com/Alibaba-NLP/OmniSearch. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02937v3-abstract-full').style.display = 'none'; document.getElementById('2411.02937v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.02864">arXiv:2411.02864</a> <span> [<a href="https://arxiv.org/pdf/2411.02864">pdf</a>, <a href="https://arxiv.org/format/2411.02864">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="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> Graph-DPEP: Decomposed Plug and Ensemble Play for Few-Shot Document Relation Extraction with Graph-of-Thoughts Reasoning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+T">Tao Zhang</a>, <a href="/search/cs?searchtype=author&query=Yan%2C+N">Ning Yan</a>, <a href="/search/cs?searchtype=author&query=Mortazavi%2C+M">Masood Mortazavi</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+H+H">Hoang H. Nguyen</a>, <a href="/search/cs?searchtype=author&query=Deng%2C+Z">Zhongfen Deng</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2411.02864v1-abstract-short" style="display: inline;"> Large language models (LLMs) pre-trained on massive corpora have demonstrated impressive few-shot learning capability on many NLP tasks. Recasting an NLP task into a text-to-text generation task is a common practice so that generative LLMs can be prompted to resolve it. However, performing document-level relation extraction (DocRE) tasks with generative LLM models is still challenging due to the s… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02864v1-abstract-full').style.display = 'inline'; document.getElementById('2411.02864v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.02864v1-abstract-full" style="display: none;"> Large language models (LLMs) pre-trained on massive corpora have demonstrated impressive few-shot learning capability on many NLP tasks. Recasting an NLP task into a text-to-text generation task is a common practice so that generative LLMs can be prompted to resolve it. However, performing document-level relation extraction (DocRE) tasks with generative LLM models is still challenging due to the structured output format of DocRE, which complicates the conversion to plain text. Limited information available in few-shot samples and prompt instructions induce further difficulties and challenges in relation extraction for mentioned entities in a document. In this paper, we represent the structured output as a graph-style triplet rather than natural language expressions and leverage generative LLMs for the DocRE task. Our approach, the Graph-DPEP framework is grounded in the reasoning behind triplet explanation thoughts presented in natural language. In this framework, we first introduce a ``decomposed-plug" method for performing the generation from LLMs over prompts with type-space decomposition to alleviate the burden of distinguishing all relation types. Second, we employ a verifier for calibrating the generation and identifying overlooked query entity pairs. Third, we develop "ensemble-play", reapplying generation on the entire type list by leveraging the reasoning thoughts embedded in a sub-graph associated with the missing query pair to address the missingness issue. Through extensive comparisons with existing prompt techniques and alternative Language Models (LLMs), our framework demonstrates superior performance on publicly available benchmarks in experiments. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02864v1-abstract-full').style.display = 'none'; document.getElementById('2411.02864v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.02398">arXiv:2411.02398</a> <span> [<a href="https://arxiv.org/pdf/2411.02398">pdf</a>, <a href="https://arxiv.org/format/2411.02398">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"> Prompting with Phonemes: Enhancing LLM Multilinguality for non-Latin Script Languages </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+H">Hoang Nguyen</a>, <a href="/search/cs?searchtype=author&query=Mahajan%2C+K">Khyati Mahajan</a>, <a href="/search/cs?searchtype=author&query=Yadav%2C+V">Vikas Yadav</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. Yu</a>, <a href="/search/cs?searchtype=author&query=Hashemi%2C+M">Masoud Hashemi</a>, <a href="/search/cs?searchtype=author&query=Maheshwary%2C+R">Rishabh Maheshwary</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="2411.02398v1-abstract-short" style="display: inline;"> Multilingual LLMs have achieved remarkable benchmark performance, but we find they continue to underperform on non-Latin script languages across contemporary LLM families. This discrepancy arises from the fact that LLMs are pretrained with orthographic scripts, which are dominated by Latin characters that obscure their shared phonology with non-Latin scripts. We propose leveraging phonemic transcr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02398v1-abstract-full').style.display = 'inline'; document.getElementById('2411.02398v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.02398v1-abstract-full" style="display: none;"> Multilingual LLMs have achieved remarkable benchmark performance, but we find they continue to underperform on non-Latin script languages across contemporary LLM families. This discrepancy arises from the fact that LLMs are pretrained with orthographic scripts, which are dominated by Latin characters that obscure their shared phonology with non-Latin scripts. We propose leveraging phonemic transcriptions as complementary signals to induce script-invariant representations. Our study demonstrates that integrating phonemic signals improves performance across both non-Latin and Latin languages, with a particularly significant impact on closing the performance gap between the two. Through detailed experiments, we show that phonemic and orthographic scripts retrieve distinct examples for in-context learning (ICL). This motivates our proposed Mixed-ICL retrieval strategy, where further aggregation leads to our significant performance improvements for both Latin script languages (up to 12.6%) and non-Latin script languages (up to 15.1%) compared to randomized ICL retrieval. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.02398v1-abstract-full').style.display = 'none'; document.getElementById('2411.02398v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.21523">arXiv:2410.21523</a> <span> [<a href="https://arxiv.org/pdf/2410.21523">pdf</a>, <a href="https://arxiv.org/format/2410.21523">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Diffusion-nested Auto-Regressive Synthesis of Heterogeneous Tabular Data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+H">Hengrui Zhang</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+L">Liancheng Fang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Q">Qitian Wu</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2410.21523v1-abstract-short" style="display: inline;"> Autoregressive models are predominant in natural language generation, while their application in tabular data remains underexplored. We posit that this can be attributed to two factors: 1) tabular data contains heterogeneous data type, while the autoregressive model is primarily designed to model discrete-valued data; 2) tabular data is column permutation-invariant, requiring a generation model to… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21523v1-abstract-full').style.display = 'inline'; document.getElementById('2410.21523v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.21523v1-abstract-full" style="display: none;"> Autoregressive models are predominant in natural language generation, while their application in tabular data remains underexplored. We posit that this can be attributed to two factors: 1) tabular data contains heterogeneous data type, while the autoregressive model is primarily designed to model discrete-valued data; 2) tabular data is column permutation-invariant, requiring a generation model to generate columns in arbitrary order. This paper proposes a Diffusion-nested Autoregressive model (TabDAR) to address these issues. To enable autoregressive methods for continuous columns, TabDAR employs a diffusion model to parameterize the conditional distribution of continuous features. To ensure arbitrary generation order, TabDAR resorts to masked transformers with bi-directional attention, which simulate various permutations of column order, hence enabling it to learn the conditional distribution of a target column given an arbitrary combination of other columns. These designs enable TabDAR to not only freely handle heterogeneous tabular data but also support convenient and flexible unconditional/conditional sampling. We conduct extensive experiments on ten datasets with distinct properties, and the proposed TabDAR outperforms previous state-of-the-art methods by 18% to 45% on eight metrics across three distinct aspects. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21523v1-abstract-full').style.display = 'none'; document.getElementById('2410.21523v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">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/2410.17941">arXiv:2410.17941</a> <span> [<a href="https://arxiv.org/pdf/2410.17941">pdf</a>, <a href="https://arxiv.org/format/2410.17941">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Spiking Graph Neural Network on Riemannian Manifolds </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sun%2C+L">Li Sun</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+Z">Zhenhao Huang</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+Q">Qiqi Wan</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+H">Hao Peng</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2410.17941v1-abstract-short" style="display: inline;"> Graph neural networks (GNNs) have become the dominant solution for learning on graphs, the typical non-Euclidean structures. Conventional GNNs, constructed with the Artificial Neuron Network (ANN), have achieved impressive performance at the cost of high computation and energy consumption. In parallel, spiking GNNs with brain-like spiking neurons are drawing increasing research attention owing to… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17941v1-abstract-full').style.display = 'inline'; document.getElementById('2410.17941v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.17941v1-abstract-full" style="display: none;"> Graph neural networks (GNNs) have become the dominant solution for learning on graphs, the typical non-Euclidean structures. Conventional GNNs, constructed with the Artificial Neuron Network (ANN), have achieved impressive performance at the cost of high computation and energy consumption. In parallel, spiking GNNs with brain-like spiking neurons are drawing increasing research attention owing to the energy efficiency. So far, existing spiking GNNs consider graphs in Euclidean space, ignoring the structural geometry, and suffer from the high latency issue due to Back-Propagation-Through-Time (BPTT) with the surrogate gradient. In light of the aforementioned issues, we are devoted to exploring spiking GNN on Riemannian manifolds, and present a Manifold-valued Spiking GNN (MSG). In particular, we design a new spiking neuron on geodesically complete manifolds with the diffeomorphism, so that BPTT regarding the spikes is replaced by the proposed differentiation via manifold. Theoretically, we show that MSG approximates a solver of the manifold ordinary differential equation. Extensive experiments on common graphs show the proposed MSG achieves superior performance to previous spiking GNNs and energy efficiency to conventional GNNs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17941v1-abstract-full').style.display = 'none'; document.getElementById('2410.17941v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by NeurIPS 2024, 30 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/2410.16386">arXiv:2410.16386</a> <span> [<a href="https://arxiv.org/pdf/2410.16386">pdf</a>, <a href="https://arxiv.org/format/2410.16386">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> </div> </div> <p class="title is-5 mathjax"> LEGO-Learn: Label-Efficient Graph Open-Set Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xu%2C+H">Haoyan Xu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+K">Kay Liu</a>, <a href="/search/cs?searchtype=author&query=Yao%2C+Z">Zhengtao Yao</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. Yu</a>, <a href="/search/cs?searchtype=author&query=Ding%2C+K">Kaize Ding</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Y">Yue Zhao</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="2410.16386v1-abstract-short" style="display: inline;"> How can we train graph-based models to recognize unseen classes while keeping labeling costs low? Graph open-set learning (GOL) and out-of-distribution (OOD) detection aim to address this challenge by training models that can accurately classify known, in-distribution (ID) classes while identifying and handling previously unseen classes during inference. It is critical for high-stakes, real-world… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.16386v1-abstract-full').style.display = 'inline'; document.getElementById('2410.16386v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.16386v1-abstract-full" style="display: none;"> How can we train graph-based models to recognize unseen classes while keeping labeling costs low? Graph open-set learning (GOL) and out-of-distribution (OOD) detection aim to address this challenge by training models that can accurately classify known, in-distribution (ID) classes while identifying and handling previously unseen classes during inference. It is critical for high-stakes, real-world applications where models frequently encounter unexpected data, including finance, security, and healthcare. However, current GOL methods assume access to many labeled ID samples, which is unrealistic for large-scale graphs due to high annotation costs. In this paper, we propose LEGO-Learn (Label-Efficient Graph Open-set Learning), a novel framework that tackles open-set node classification on graphs within a given label budget by selecting the most informative ID nodes. LEGO-Learn employs a GNN-based filter to identify and exclude potential OOD nodes and then select highly informative ID nodes for labeling using the K-Medoids algorithm. To prevent the filter from discarding valuable ID examples, we introduce a classifier that differentiates between the C known ID classes and an additional class representing OOD nodes (hence, a C+1 classifier). This classifier uses a weighted cross-entropy loss to balance the removal of OOD nodes while retaining informative ID nodes. Experimental results on four real-world datasets demonstrate that LEGO-Learn significantly outperforms leading methods, with up to a 6.62% improvement in ID classification accuracy and a 7.49% increase in AUROC for OOD detection. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.16386v1-abstract-full').style.display = 'none'; document.getElementById('2410.16386v1-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Preprint. Under review</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.09348">arXiv:2410.09348</a> <span> [<a href="https://arxiv.org/pdf/2410.09348">pdf</a>, <a href="https://arxiv.org/format/2410.09348">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> </div> </div> <p class="title is-5 mathjax"> BANGS: Game-Theoretic Node Selection for Graph Self-Training </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+F">Fangxin Wang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+K">Kay Liu</a>, <a href="/search/cs?searchtype=author&query=Medya%2C+S">Sourav Medya</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2410.09348v1-abstract-short" style="display: inline;"> Graph self-training is a semi-supervised learning method that iteratively selects a set of unlabeled data to retrain the underlying graph neural network (GNN) model and improve its prediction performance. While selecting highly confident nodes has proven effective for self-training, this pseudo-labeling strategy ignores the combinatorial dependencies between nodes and suffers from a local view of… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.09348v1-abstract-full').style.display = 'inline'; document.getElementById('2410.09348v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.09348v1-abstract-full" style="display: none;"> Graph self-training is a semi-supervised learning method that iteratively selects a set of unlabeled data to retrain the underlying graph neural network (GNN) model and improve its prediction performance. While selecting highly confident nodes has proven effective for self-training, this pseudo-labeling strategy ignores the combinatorial dependencies between nodes and suffers from a local view of the distribution. To overcome these issues, we propose BANGS, a novel framework that unifies the labeling strategy with conditional mutual information as the objective of node selection. Our approach -- grounded in game theory -- selects nodes in a combinatorial fashion and provides theoretical guarantees for robustness under noisy objective. More specifically, unlike traditional methods that rank and select nodes independently, BANGS considers nodes as a collective set in the self-training process. Our method demonstrates superior performance and robustness across various datasets, base models, and hyperparameter settings, outperforming existing techniques. The codebase is available on https://github.com/fangxin-wang/BANGS . <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.09348v1-abstract-full').style.display = 'none'; document.getElementById('2410.09348v1-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Preprint</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.06340">arXiv:2410.06340</a> <span> [<a href="https://arxiv.org/pdf/2410.06340">pdf</a>, <a href="https://arxiv.org/format/2410.06340">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> FedGraph: A Research Library and Benchmark for Federated Graph Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yao%2C+Y">Yuhang Yao</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yuan Li</a>, <a href="/search/cs?searchtype=author&query=Fan%2C+X">Xinyi Fan</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Junhao Li</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+K">Kay Liu</a>, <a href="/search/cs?searchtype=author&query=Jin%2C+W">Weizhao Jin</a>, <a href="/search/cs?searchtype=author&query=Ravi%2C+S">Srivatsan Ravi</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. Yu</a>, <a href="/search/cs?searchtype=author&query=Joe-Wong%2C+C">Carlee Joe-Wong</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="2410.06340v2-abstract-short" style="display: inline;"> Federated graph learning is an emerging field with significant practical challenges. While many algorithms have been proposed to enhance the accuracy of training graph neural networks, e.g., for node classification problems on large graphs, in a federated manner, their system performance is often overlooked, even though it is crucial for real-world deployment. To address this gap, we introduce Fed… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.06340v2-abstract-full').style.display = 'inline'; document.getElementById('2410.06340v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.06340v2-abstract-full" style="display: none;"> Federated graph learning is an emerging field with significant practical challenges. While many algorithms have been proposed to enhance the accuracy of training graph neural networks, e.g., for node classification problems on large graphs, in a federated manner, their system performance is often overlooked, even though it is crucial for real-world deployment. To address this gap, we introduce FedGraph, a research library built for practical distributed deployment and benchmarking in federated graph learning. FedGraph supports a range of state-of-the-art graph learning methods and includes built-in profiling tools to evaluate system performance, focusing specifically on communication and computation costs during training. Unlike existing benchmark platforms, FedGraph natively incorporates homomorphic encryption to enhance privacy preservation and facilitates the development of practical applications by enabling distributed training across multiple physical machines, providing an evaluation framework that can guide the system design of future federated graph learning algorithms. Leveraging these optimizations, we use FedGraph to demonstrate the first privacy-preserving federated learning system to run on graphs with 100 million nodes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.06340v2-abstract-full').style.display = 'none'; document.getElementById('2410.06340v2-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, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 8 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">https://github.com/FedGraph/fedgraph</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.05352">arXiv:2410.05352</a> <span> [<a href="https://arxiv.org/pdf/2410.05352">pdf</a>, <a href="https://arxiv.org/format/2410.05352">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"> Recent Advances of Multimodal Continual Learning: A Comprehensive Survey </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yu%2C+D">Dianzhi Yu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+X">Xinni Zhang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yankai Chen</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+A">Aiwei Liu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yifei Zhang</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. Yu</a>, <a href="/search/cs?searchtype=author&query=King%2C+I">Irwin King</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="2410.05352v2-abstract-short" style="display: inline;"> Continual learning (CL) aims to empower machine learning models to learn continually from new data, while building upon previously acquired knowledge without forgetting. As machine learning models have evolved from small to large pre-trained architectures, and from supporting unimodal to multimodal data, multimodal continual learning (MMCL) methods have recently emerged. The primary challenge of M… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.05352v2-abstract-full').style.display = 'inline'; document.getElementById('2410.05352v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.05352v2-abstract-full" style="display: none;"> Continual learning (CL) aims to empower machine learning models to learn continually from new data, while building upon previously acquired knowledge without forgetting. As machine learning models have evolved from small to large pre-trained architectures, and from supporting unimodal to multimodal data, multimodal continual learning (MMCL) methods have recently emerged. The primary challenge of MMCL is that it goes beyond a simple stacking of unimodal CL methods, as such straightforward approaches often yield unsatisfactory performance. In this work, we present the first comprehensive survey on MMCL. We provide essential background knowledge and MMCL settings, as well as a structured taxonomy of MMCL methods. We categorize existing MMCL methods into four categories, i.e., regularization-based, architecture-based, replay-based, and prompt-based methods, explaining their methodologies and highlighting their key innovations. Additionally, to prompt further research in this field, we summarize open MMCL datasets and benchmarks, and discuss several promising future directions for investigation and development. We have also created a GitHub repository for indexing relevant MMCL papers and open resources available at https://github.com/LucyDYu/Awesome-Multimodal-Continual-Learning. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.05352v2-abstract-full').style.display = 'none'; document.getElementById('2410.05352v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 7 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/2410.04756">arXiv:2410.04756</a> <span> [<a href="https://arxiv.org/pdf/2410.04756">pdf</a>, <a href="https://arxiv.org/format/2410.04756">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="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"> Item Cluster-aware Prompt Learning for Session-based Recommendation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+W">Wooseong Yang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+C">Chen Wang</a>, <a href="/search/cs?searchtype=author&query=Song%2C+Z">Zihe Song</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+W">Weizhi Zhang</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2410.04756v1-abstract-short" style="display: inline;"> Session-based recommendation (SBR) aims to capture dynamic user preferences by analyzing item sequences within individual sessions. However, most existing approaches focus mainly on intra-session item relationships, neglecting the connections between items across different sessions (inter-session relationships), which limits their ability to fully capture complex item interactions. While some meth… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04756v1-abstract-full').style.display = 'inline'; document.getElementById('2410.04756v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.04756v1-abstract-full" style="display: none;"> Session-based recommendation (SBR) aims to capture dynamic user preferences by analyzing item sequences within individual sessions. However, most existing approaches focus mainly on intra-session item relationships, neglecting the connections between items across different sessions (inter-session relationships), which limits their ability to fully capture complex item interactions. While some methods incorporate inter-session information, they often suffer from high computational costs, leading to longer training times and reduced efficiency. To address these challenges, we propose the CLIP-SBR (Cluster-aware Item Prompt learning for Session-Based Recommendation) framework. CLIP-SBR is composed of two modules: 1) an item relationship mining module that builds a global graph to effectively model both intra- and inter-session relationships, and 2) an item cluster-aware prompt learning module that uses soft prompts to integrate these relationships into SBR models efficiently. We evaluate CLIP-SBR across eight SBR models and three benchmark datasets, consistently demonstrating improved recommendation performance and establishing CLIP-SBR as a robust solution for session-based recommendation tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04756v1-abstract-full').style.display = 'none'; document.getElementById('2410.04756v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">9 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/2410.04509">arXiv:2410.04509</a> <span> [<a href="https://arxiv.org/pdf/2410.04509">pdf</a>, <a href="https://arxiv.org/format/2410.04509">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"> ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yan%2C+Y">Yibo Yan</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Shen Wang</a>, <a href="/search/cs?searchtype=author&query=Huo%2C+J">Jiahao Huo</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Hang Li</a>, <a href="/search/cs?searchtype=author&query=Li%2C+B">Boyan Li</a>, <a href="/search/cs?searchtype=author&query=Su%2C+J">Jiamin Su</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+X">Xiong Gao</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yi-Fan Zhang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+T">Tianlong Xu</a>, <a href="/search/cs?searchtype=author&query=Chu%2C+Z">Zhendong Chu</a>, <a href="/search/cs?searchtype=author&query=Zhong%2C+A">Aoxiao Zhong</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+K">Kun Wang</a>, <a href="/search/cs?searchtype=author&query=Xiong%2C+H">Hui Xiong</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. Yu</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+X">Xuming Hu</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+Q">Qingsong Wen</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="2410.04509v2-abstract-short" style="display: inline;"> As the field of Multimodal Large Language Models (MLLMs) continues to evolve, their potential to revolutionize artificial intelligence is particularly promising, especially in addressing mathematical reasoning tasks. Current mathematical benchmarks predominantly focus on evaluating MLLMs' problem-solving ability, yet there is a crucial gap in addressing more complex scenarios such as error detecti… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04509v2-abstract-full').style.display = 'inline'; document.getElementById('2410.04509v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.04509v2-abstract-full" style="display: none;"> As the field of Multimodal Large Language Models (MLLMs) continues to evolve, their potential to revolutionize artificial intelligence is particularly promising, especially in addressing mathematical reasoning tasks. Current mathematical benchmarks predominantly focus on evaluating MLLMs' problem-solving ability, yet there is a crucial gap in addressing more complex scenarios such as error detection, for enhancing reasoning capability in complicated settings. To fill this gap, we formally formulate the new task: multimodal error detection, and introduce ErrorRadar, the first benchmark designed to assess MLLMs' capabilities in such a task. ErrorRadar evaluates two sub-tasks: error step identification and error categorization, providing a comprehensive framework for evaluating MLLMs' complex mathematical reasoning ability. It consists of 2,500 high-quality multimodal K-12 mathematical problems, collected from real-world student interactions in an educational organization, with rigorous annotation and rich metadata such as problem type and error category. Through extensive experiments, we evaluated both open-source and closed-source representative MLLMs, benchmarking their performance against educational expert evaluators. Results indicate significant challenges still remain, as GPT-4o with best performance is still around 10% behind human evaluation. The dataset will be available upon acceptance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04509v2-abstract-full').style.display = 'none'; document.getElementById('2410.04509v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 6 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/2410.04350">arXiv:2410.04350</a> <span> [<a href="https://arxiv.org/pdf/2410.04350">pdf</a>, <a href="https://arxiv.org/format/2410.04350">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"> TIS-DPO: Token-level Importance Sampling for Direct Preference Optimization With Estimated Weights </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+A">Aiwei Liu</a>, <a href="/search/cs?searchtype=author&query=Bai%2C+H">Haoping Bai</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+Z">Zhiyun Lu</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+Y">Yanchao Sun</a>, <a href="/search/cs?searchtype=author&query=Kong%2C+X">Xiang Kong</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Simon Wang</a>, <a href="/search/cs?searchtype=author&query=Shan%2C+J">Jiulong Shan</a>, <a href="/search/cs?searchtype=author&query=Jose%2C+A+M">Albin Madappally Jose</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xiaojiang Liu</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+L">Lijie Wen</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. Yu</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+M">Meng Cao</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="2410.04350v2-abstract-short" style="display: inline;"> Direct Preference Optimization (DPO) has been widely adopted for preference alignment of Large Language Models (LLMs) due to its simplicity and effectiveness. However, DPO is derived as a bandit problem in which the whole response is treated as a single arm, ignoring the importance differences between tokens, which may affect optimization efficiency and make it difficult to achieve optimal results… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04350v2-abstract-full').style.display = 'inline'; document.getElementById('2410.04350v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.04350v2-abstract-full" style="display: none;"> Direct Preference Optimization (DPO) has been widely adopted for preference alignment of Large Language Models (LLMs) due to its simplicity and effectiveness. However, DPO is derived as a bandit problem in which the whole response is treated as a single arm, ignoring the importance differences between tokens, which may affect optimization efficiency and make it difficult to achieve optimal results. In this work, we propose that the optimal data for DPO has equal expected rewards for each token in winning and losing responses, as there is no difference in token importance. However, since the optimal dataset is unavailable in practice, we propose using the original dataset for importance sampling to achieve unbiased optimization. Accordingly, we propose a token-level importance sampling DPO objective named TIS-DPO that assigns importance weights to each token based on its reward. Inspired by previous works, we estimate the token importance weights using the difference in prediction probabilities from a pair of contrastive LLMs. We explore three methods to construct these contrastive LLMs: (1) guiding the original LLM with contrastive prompts, (2) training two separate LLMs using winning and losing responses, and (3) performing forward and reverse DPO training with winning and losing responses. Experiments show that TIS-DPO significantly outperforms various baseline methods on harmlessness and helpfulness alignment and summarization tasks. We also visualize the estimated weights, demonstrating their ability to identify key token positions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04350v2-abstract-full').style.display = 'none'; document.getElementById('2410.04350v2-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 6 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">30 pages, 8 figures, 8 tables, Published in ICLR 2025</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68T50 <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.2.7 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.03168">arXiv:2410.03168</a> <span> [<a href="https://arxiv.org/pdf/2410.03168">pdf</a>, <a href="https://arxiv.org/format/2410.03168">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="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Can Watermarked LLMs be Identified by Users via Crafted Prompts? </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+A">Aiwei Liu</a>, <a href="/search/cs?searchtype=author&query=Guan%2C+S">Sheng Guan</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yiming Liu</a>, <a href="/search/cs?searchtype=author&query=Pan%2C+L">Leyi Pan</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yifei Zhang</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+L">Liancheng Fang</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+L">Lijie Wen</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. Yu</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+X">Xuming Hu</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="2410.03168v3-abstract-short" style="display: inline;"> Text watermarking for Large Language Models (LLMs) has made significant progress in detecting LLM outputs and preventing misuse. Current watermarking techniques offer high detectability, minimal impact on text quality, and robustness to text editing. However, current researches lack investigation into the imperceptibility of watermarking techniques in LLM services. This is crucial as LLM providers… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.03168v3-abstract-full').style.display = 'inline'; document.getElementById('2410.03168v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.03168v3-abstract-full" style="display: none;"> Text watermarking for Large Language Models (LLMs) has made significant progress in detecting LLM outputs and preventing misuse. Current watermarking techniques offer high detectability, minimal impact on text quality, and robustness to text editing. However, current researches lack investigation into the imperceptibility of watermarking techniques in LLM services. This is crucial as LLM providers may not want to disclose the presence of watermarks in real-world scenarios, as it could reduce user willingness to use the service and make watermarks more vulnerable to attacks. This work is the first to investigate the imperceptibility of watermarked LLMs. We design an identification algorithm called Water-Probe that detects watermarks through well-designed prompts to the LLM. Our key motivation is that current watermarked LLMs expose consistent biases under the same watermark key, resulting in similar differences across prompts under different watermark keys. Experiments show that almost all mainstream watermarking algorithms are easily identified with our well-designed prompts, while Water-Probe demonstrates a minimal false positive rate for non-watermarked LLMs. Finally, we propose that the key to enhancing the imperceptibility of watermarked LLMs is to increase the randomness of watermark key selection. Based on this, we introduce the Water-Bag strategy, which significantly improves watermark imperceptibility by merging multiple watermark keys. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.03168v3-abstract-full').style.display = 'none'; document.getElementById('2410.03168v3-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 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">28 pages, 5 figures, 11 tables Published as a conference paper at ICLR 2025 Github link: https://github.com/THU-BPM/Watermarked_LLM_Identification</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68T50 <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.2.7 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.10102">arXiv:2409.10102</a> <span> [<a href="https://arxiv.org/pdf/2409.10102">pdf</a>, <a href="https://arxiv.org/format/2409.10102">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="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"> Trustworthiness in Retrieval-Augmented Generation Systems: A Survey </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhou%2C+Y">Yujia Zhou</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yan Liu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xiaoxi Li</a>, <a href="/search/cs?searchtype=author&query=Jin%2C+J">Jiajie Jin</a>, <a href="/search/cs?searchtype=author&query=Qian%2C+H">Hongjin Qian</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zheng Liu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+C">Chaozhuo Li</a>, <a href="/search/cs?searchtype=author&query=Dou%2C+Z">Zhicheng Dou</a>, <a href="/search/cs?searchtype=author&query=Ho%2C+T">Tsung-Yi Ho</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2409.10102v1-abstract-short" style="display: inline;"> Retrieval-Augmented Generation (RAG) has quickly grown into a pivotal paradigm in the development of Large Language Models (LLMs). While much of the current research in this field focuses on performance optimization, particularly in terms of accuracy and efficiency, the trustworthiness of RAG systems remains an area still under exploration. From a positive perspective, RAG systems are promising to… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.10102v1-abstract-full').style.display = 'inline'; document.getElementById('2409.10102v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.10102v1-abstract-full" style="display: none;"> Retrieval-Augmented Generation (RAG) has quickly grown into a pivotal paradigm in the development of Large Language Models (LLMs). While much of the current research in this field focuses on performance optimization, particularly in terms of accuracy and efficiency, the trustworthiness of RAG systems remains an area still under exploration. From a positive perspective, RAG systems are promising to enhance LLMs by providing them with useful and up-to-date knowledge from vast external databases, thereby mitigating the long-standing problem of hallucination. While from a negative perspective, RAG systems are at the risk of generating undesirable contents if the retrieved information is either inappropriate or poorly utilized. To address these concerns, we propose a unified framework that assesses the trustworthiness of RAG systems across six key dimensions: factuality, robustness, fairness, transparency, accountability, and privacy. Within this framework, we thoroughly review the existing literature on each dimension. Additionally, we create the evaluation benchmark regarding the six dimensions and conduct comprehensive evaluations for a variety of proprietary and open-source models. Finally, we identify the potential challenges for future research based on our investigation results. Through this work, we aim to lay a structured foundation for future investigations and provide practical insights for enhancing the trustworthiness of RAG systems in real-world applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.10102v1-abstract-full').style.display = 'none'; document.getElementById('2409.10102v1-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.05112">arXiv:2409.05112</a> <span> [<a href="https://arxiv.org/pdf/2409.05112">pdf</a>, <a href="https://arxiv.org/format/2409.05112">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"> WaterSeeker: Pioneering Efficient Detection of Watermarked Segments in Large Documents </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pan%2C+L">Leyi Pan</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+A">Aiwei Liu</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+Y">Yijian Lu</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+Z">Zitian Gao</a>, <a href="/search/cs?searchtype=author&query=Di%2C+Y">Yichen Di</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+S">Shiyu Huang</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+L">Lijie Wen</a>, <a href="/search/cs?searchtype=author&query=King%2C+I">Irwin King</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2409.05112v5-abstract-short" style="display: inline;"> Watermarking algorithms for large language models (LLMs) have attained high accuracy in detecting LLM-generated text. However, existing methods primarily focus on distinguishing fully watermarked text from non-watermarked text, overlooking real-world scenarios where LLMs generate only small sections within large documents. In this scenario, balancing time complexity and detection performance poses… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.05112v5-abstract-full').style.display = 'inline'; document.getElementById('2409.05112v5-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.05112v5-abstract-full" style="display: none;"> Watermarking algorithms for large language models (LLMs) have attained high accuracy in detecting LLM-generated text. However, existing methods primarily focus on distinguishing fully watermarked text from non-watermarked text, overlooking real-world scenarios where LLMs generate only small sections within large documents. In this scenario, balancing time complexity and detection performance poses significant challenges. This paper presents WaterSeeker, a novel approach to efficiently detect and locate watermarked segments amid extensive natural text. It first applies an efficient anomaly extraction method to preliminarily locate suspicious watermarked regions. Following this, it conducts a local traversal and performs full-text detection for more precise verification. Theoretical analysis and experimental results demonstrate that WaterSeeker achieves a superior balance between detection accuracy and computational efficiency. Moreover, its localization capability lays the foundation for building interpretable AI detection systems. Our code is available at https://github.com/THU-BPM/WaterSeeker. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.05112v5-abstract-full').style.display = 'none'; document.getElementById('2409.05112v5-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 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 8 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">NAACL 2025 Findings</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68T50 <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.2.7 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.00614">arXiv:2409.00614</a> <span> [<a href="https://arxiv.org/pdf/2409.00614">pdf</a>, <a href="https://arxiv.org/format/2409.00614">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> DAMe: Personalized Federated Social Event Detection with Dual Aggregation Mechanism </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yu%2C+X">Xiaoyan Yu</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+Y">Yifan Wei</a>, <a href="/search/cs?searchtype=author&query=Li%2C+P">Pu Li</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+S">Shuaishuai Zhou</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+H">Hao Peng</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+L">Li Sun</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+L">Liehuang Zhu</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2409.00614v1-abstract-short" style="display: inline;"> Training social event detection models through federated learning (FedSED) aims to improve participants' performance on the task. However, existing federated learning paradigms are inadequate for achieving FedSED's objective and exhibit limitations in handling the inherent heterogeneity in social data. This paper proposes a personalized federated learning framework with a dual aggregation mechanis… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.00614v1-abstract-full').style.display = 'inline'; document.getElementById('2409.00614v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.00614v1-abstract-full" style="display: none;"> Training social event detection models through federated learning (FedSED) aims to improve participants' performance on the task. However, existing federated learning paradigms are inadequate for achieving FedSED's objective and exhibit limitations in handling the inherent heterogeneity in social data. This paper proposes a personalized federated learning framework with a dual aggregation mechanism for social event detection, namely DAMe. We present a novel local aggregation strategy utilizing Bayesian optimization to incorporate global knowledge while retaining local characteristics. Moreover, we introduce a global aggregation strategy to provide clients with maximum external knowledge of their preferences. In addition, we incorporate a global-local event-centric constraint to prevent local overfitting and ``client-drift''. Experiments within a realistic simulation of a natural federated setting, utilizing six social event datasets spanning six languages and two social media platforms, along with an ablation study, have demonstrated the effectiveness of the proposed framework. Further robustness analyses have shown that DAMe is resistant to injection attacks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.00614v1-abstract-full').style.display = 'none'; document.getElementById('2409.00614v1-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 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">CIKM 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.00089">arXiv:2409.00089</a> <span> [<a href="https://arxiv.org/pdf/2409.00089">pdf</a>, <a href="https://arxiv.org/format/2409.00089">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="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Watermarking Techniques for Large Language Models: A Survey </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liang%2C+Y">Yuqing Liang</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+J">Jiancheng Xiao</a>, <a href="/search/cs?searchtype=author&query=Gan%2C+W">Wensheng Gan</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2409.00089v1-abstract-short" style="display: inline;"> With the rapid advancement and extensive application of artificial intelligence technology, large language models (LLMs) are extensively used to enhance production, creativity, learning, and work efficiency across various domains. However, the abuse of LLMs also poses potential harm to human society, such as intellectual property rights issues, academic misconduct, false content, and hallucination… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.00089v1-abstract-full').style.display = 'inline'; document.getElementById('2409.00089v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.00089v1-abstract-full" style="display: none;"> With the rapid advancement and extensive application of artificial intelligence technology, large language models (LLMs) are extensively used to enhance production, creativity, learning, and work efficiency across various domains. However, the abuse of LLMs also poses potential harm to human society, such as intellectual property rights issues, academic misconduct, false content, and hallucinations. Relevant research has proposed the use of LLM watermarking to achieve IP protection for LLMs and traceability of multimedia data output by LLMs. To our knowledge, this is the first thorough review that investigates and analyzes LLM watermarking technology in detail. This review begins by recounting the history of traditional watermarking technology, then analyzes the current state of LLM watermarking research, and thoroughly examines the inheritance and relevance of these techniques. By analyzing their inheritance and relevance, this review can provide research with ideas for applying traditional digital watermarking techniques to LLM watermarking, to promote the cross-integration and innovation of watermarking technology. In addition, this review examines the pros and cons of LLM watermarking. Considering the current multimodal development trend of LLMs, it provides a detailed analysis of emerging multimodal LLM watermarking, such as visual and audio data, to offer more reference ideas for relevant research. This review delves into the challenges and future prospects of current watermarking technologies, offering valuable insights for future LLM watermarking research and applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.00089v1-abstract-full').style.display = 'none'; document.getElementById('2409.00089v1-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 August, 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">Preprint. 19 figures, 7 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.14155">arXiv:2408.14155</a> <span> [<a href="https://arxiv.org/pdf/2408.14155">pdf</a>, <a href="https://arxiv.org/format/2408.14155">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> Digital Fingerprinting on Multimedia: A Survey </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+W">Wendi Chen</a>, <a href="/search/cs?searchtype=author&query=Gan%2C+W">Wensheng Gan</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2408.14155v1-abstract-short" style="display: inline;"> The explosive growth of multimedia content in the digital economy era has brought challenges in content recognition, copyright protection, and data management. As an emerging content management technology, perceptual hash-based digital fingerprints, serving as compact summaries of multimedia content, have been widely adopted for efficient multimedia content identification and retrieval across diff… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.14155v1-abstract-full').style.display = 'inline'; document.getElementById('2408.14155v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.14155v1-abstract-full" style="display: none;"> The explosive growth of multimedia content in the digital economy era has brought challenges in content recognition, copyright protection, and data management. As an emerging content management technology, perceptual hash-based digital fingerprints, serving as compact summaries of multimedia content, have been widely adopted for efficient multimedia content identification and retrieval across different modalities (e.g., text, image, video, audio), attracting significant attention from both academia and industry. Despite the increasing applications of digital fingerprints, there is a lack of systematic and comprehensive literature review on multimedia digital fingerprints. This survey aims to fill this gap and provide an important resource for researchers studying the details and related advancements of multimedia digital fingerprints. The survey first introduces the definition, characteristics, and related concepts (including hash functions, granularity, similarity measures, etc.) of digital fingerprints. It then focuses on analyzing and summarizing the algorithms for extracting unimodal fingerprints of different types of digital content, including text fingerprints, image fingerprints, video fingerprints, and audio fingerprints. Particularly, it provides an in-depth review and summary of deep learning-based fingerprints. Additionally, the survey elaborates on the various practical applications of digital fingerprints and outlines the challenges and potential future research directions. The goal is to promote the continued development of multimedia digital fingerprint research. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.14155v1-abstract-full').style.display = 'none'; document.getElementById('2408.14155v1-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 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">Preprint. 5 figures, 7 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.05200">arXiv:2408.05200</a> <span> [<a href="https://arxiv.org/pdf/2408.05200">pdf</a>, <a href="https://arxiv.org/format/2408.05200">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> KIF: Knowledge Identification and Fusion for Language Model Continual Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Feng%2C+Y">Yujie Feng</a>, <a href="/search/cs?searchtype=author&query=Chu%2C+X">Xu Chu</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Y">Yongxin Xu</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+Z">Zexin Lu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+B">Bo Liu</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. Yu</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+X">Xiao-Ming Wu</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="2408.05200v4-abstract-short" style="display: inline;"> Language model continual learning (CL) has recently attracted significant interest for its ability to adapt large language models (LLMs) to dynamic real-world scenarios without retraining. A major challenge in this domain is catastrophic forgetting, where models lose previously acquired knowledge upon learning new tasks. Existing approaches commonly utilize multiple parameter-efficient fine-tuning… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.05200v4-abstract-full').style.display = 'inline'; document.getElementById('2408.05200v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.05200v4-abstract-full" style="display: none;"> Language model continual learning (CL) has recently attracted significant interest for its ability to adapt large language models (LLMs) to dynamic real-world scenarios without retraining. A major challenge in this domain is catastrophic forgetting, where models lose previously acquired knowledge upon learning new tasks. Existing approaches commonly utilize multiple parameter-efficient fine-tuning (PEFT) blocks to acquire task-specific knowledge, yet these methods are inefficient and fail to leverage potential knowledge transfer across tasks. In this paper, we introduce a novel CL framework for language models, named Knowledge Identification and Fusion (KIF), which boosts knowledge transfer without depending on memory replay. KIF initially segregates the model into 'skill units' based on parameter dependencies, allowing for more precise control. Subsequently, it employs a novel group-wise knowledge identification technique to ascertain the importance distribution of skill units for a new task. By comparing this importance distribution with those from previous tasks, we implement a fine-grained knowledge fusion strategy that retains task-specific knowledge, thereby preventing forgetting, and updates task-shared knowledge, which facilitates bi-directional knowledge transfer. As a result, KIF achieves an optimal balance between retaining prior knowledge and excelling in new tasks. KIF also demonstrates strong generalizability, making it suitable for various base models and adaptable to PEFT methods like LoRA. Furthermore, it offers notable extensibility, supporting enhancements through integration with memory replay techniques. Comprehensive experiments conducted on two CL benchmarks, involving models ranging from 220M to 7B parameters, affirm the effectiveness of KIF and its variants across different settings. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.05200v4-abstract-full').style.display = 'none'; document.getElementById('2408.05200v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 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">This version updates the model name from Task Skill Localization and Consolidation (TaSL) to Knowledge Identification and Fusion (KIF). It is an extension of the ACL 2024 paper titled Continual Dialog State Tracking via Task Skill Localization and Consolidation</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.21364">arXiv:2407.21364</a> <span> [<a href="https://arxiv.org/pdf/2407.21364">pdf</a>, <a href="https://arxiv.org/format/2407.21364">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"> Personalized Multi-task Training for Recommender System </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+L">Liangwei Yang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zhiwei Liu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jianguo Zhang</a>, <a href="/search/cs?searchtype=author&query=Murthy%2C+R">Rithesh Murthy</a>, <a href="/search/cs?searchtype=author&query=Heinecke%2C+S">Shelby Heinecke</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+H">Huan Wang</a>, <a href="/search/cs?searchtype=author&query=Xiong%2C+C">Caiming Xiong</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+P+S">Philip S. 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="2407.21364v1-abstract-short" style="display: inline;"> In the vast landscape of internet information, recommender systems (RecSys) have become essential for guiding users through a sea of choices aligned with their preferences. These systems have applications in diverse domains, such as news feeds, game suggestions, and shopping recommendations. Personalization is a key technique in RecSys, where modern methods leverage representation learning to enco… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.21364v1-abstract-full').style.display = 'inline'; document.getElementById('2407.21364v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.21364v1-abstract-full" style="display: none;"> In the vast landscape of internet information, recommender systems (RecSys) have become essential for guiding users through a sea of choices aligned with their preferences. These systems have applications in diverse domains, such as news feeds, game suggestions, and shopping recommendations. Personalization is a key technique in RecSys, where modern methods leverage representation learning to encode user/item interactions into embeddings, forming the foundation for personalized recommendations. However, integrating information from multiple sources to enhance recommendation performance remains challenging. This paper introduces a novel approach named PMTRec, the first personalized multi-task learning algorithm to obtain comprehensive user/item embeddings from various information sources. Addressing challenges specific to personalized RecSys, we develop modules to handle personalized task weights, diverse task orientations, and variations in gradient magnitudes across tasks. PMTRec dynamically adjusts task weights based on gradient norms for each user/item, employs a Task Focusing module to align gradient combinations with the main recommendation task, and uses a Gradient Magnitude Balancing module to ensure balanced training across tasks. Through extensive experiments on three real-world datasets with different scales, we demonstrate that PMTRec significantly outperforms existing multi-task learning methods, showcasing its effectiveness in achieving enhanced recommendation accuracy by leveraging multiple tasks simultaneously. Our contributions open new avenues for advancing personalized multi-task training in recommender systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.21364v1-abstract-full').style.display = 'none'; document.getElementById('2407.21364v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">11 pages</span> </p> </li> </ol> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Yu%2C+P+S&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Yu%2C+P+S&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Yu%2C+P+S&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Yu%2C+P+S&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Yu%2C+P+S&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Yu%2C+P+S&start=200" class="pagination-link " aria-label="Page 5" aria-current="page">5 </a> </li> <li><span class="pagination-ellipsis">…</span></li> </ul> </nav> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository