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 109 results for author: <span class="mathjax">Wan, H</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=Wan%2C+H">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="Wan, H"> </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=Wan%2C+H&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="Wan, H"> <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=Wan%2C+H&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Wan%2C+H&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Wan%2C+H&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Wan%2C+H&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> </ul> </nav> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.02004">arXiv:2501.02004</a> <span> [<a href="https://arxiv.org/pdf/2501.02004">pdf</a>, <a href="https://arxiv.org/format/2501.02004">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="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> General Information Metrics for Improving AI Model Training Efficiency </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xu%2C+J">Jianfeng Xu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+C">Congcong Liu</a>, <a href="/search/cs?searchtype=author&query=Tan%2C+X">Xiaoying Tan</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+X">Xiaojie Zhu</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+A">Anpeng Wu</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Huan Wan</a>, <a href="/search/cs?searchtype=author&query=Kong%2C+W">Weijun Kong</a>, <a href="/search/cs?searchtype=author&query=Li%2C+C">Chun Li</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+H">Hu Xu</a>, <a href="/search/cs?searchtype=author&query=Kuang%2C+K">Kun Kuang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+F">Fei 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="2501.02004v1-abstract-short" style="display: inline;"> To address the growing size of AI model training data and the lack of a universal data selection methodology-factors that significantly drive up training costs -- this paper presents the General Information Metrics Evaluation (GIME) method. GIME leverages general information metrics from Objective Information Theory (OIT), including volume, delay, scope, granularity, variety, duration, sampling ra… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.02004v1-abstract-full').style.display = 'inline'; document.getElementById('2501.02004v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.02004v1-abstract-full" style="display: none;"> To address the growing size of AI model training data and the lack of a universal data selection methodology-factors that significantly drive up training costs -- this paper presents the General Information Metrics Evaluation (GIME) method. GIME leverages general information metrics from Objective Information Theory (OIT), including volume, delay, scope, granularity, variety, duration, sampling rate, aggregation, coverage, distortion, and mismatch to optimize dataset selection for training purposes. Comprehensive experiments conducted across diverse domains, such as CTR Prediction, Civil Case Prediction, and Weather Forecasting, demonstrate that GIME effectively preserves model performance while substantially reducing both training time and costs. Additionally, applying GIME within the Judicial AI Program led to a remarkable 39.56% reduction in total model training expenses, underscoring its potential to support efficient and sustainable AI development. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.02004v1-abstract-full').style.display = 'none'; document.getElementById('2501.02004v1-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 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/2501.01238">arXiv:2501.01238</a> <span> [<a href="https://arxiv.org/pdf/2501.01238">pdf</a>, <a href="https://arxiv.org/format/2501.01238">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> EHCTNet: Enhanced Hybrid of CNN and Transformer Network for Remote Sensing Image Change Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+J">Junjie Yang</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Haibo Wan</a>, <a href="/search/cs?searchtype=author&query=Shang%2C+Z">Zhihai Shang</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="2501.01238v1-abstract-short" style="display: inline;"> Remote sensing (RS) change detection incurs a high cost because of false negatives, which are more costly than false positives. Existing frameworks, struggling to improve the Precision metric to reduce the cost of false positive, still have limitations in focusing on the change of interest, which leads to missed detections and discontinuity issues. This work tackles these issues by enhancing featu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.01238v1-abstract-full').style.display = 'inline'; document.getElementById('2501.01238v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.01238v1-abstract-full" style="display: none;"> Remote sensing (RS) change detection incurs a high cost because of false negatives, which are more costly than false positives. Existing frameworks, struggling to improve the Precision metric to reduce the cost of false positive, still have limitations in focusing on the change of interest, which leads to missed detections and discontinuity issues. This work tackles these issues by enhancing feature learning capabilities and integrating the frequency components of feature information, with a strategy to incrementally boost the Recall value. We propose an enhanced hybrid of CNN and Transformer network (EHCTNet) for effectively mining the change information of interest. Firstly, a dual branch feature extraction module is used to extract the multi scale features of RS images. Secondly, the frequency component of these features is exploited by a refined module I. Thirdly, an enhanced token mining module based on the Kolmogorov Arnold Network is utilized to derive semantic information. Finally, the semantic change information's frequency component, beneficial for final detection, is mined from the refined module II. Extensive experiments validate the effectiveness of EHCTNet in comprehending complex changes of interest. The visualization outcomes show that EHCTNet detects more intact and continuous changed areas and perceives more accurate neighboring distinction than state of the art models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.01238v1-abstract-full').style.display = 'none'; document.getElementById('2501.01238v1-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 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/2412.16557">arXiv:2412.16557</a> <span> [<a href="https://arxiv.org/pdf/2412.16557">pdf</a>, <a href="https://arxiv.org/format/2412.16557">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"> CognTKE: A Cognitive Temporal Knowledge Extrapolation Framework </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+W">Wei Chen</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yuting Wu</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+S">Shuhan Wu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhiyu Zhang</a>, <a href="/search/cs?searchtype=author&query=Liao%2C+M">Mengqi Liao</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Youfang Lin</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Huaiyu Wan</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="2412.16557v1-abstract-short" style="display: inline;"> Reasoning future unknowable facts on temporal knowledge graphs (TKGs) is a challenging task, holding significant academic and practical values for various fields. Existing studies exploring explainable reasoning concentrate on modeling comprehensible temporal paths relevant to the query. Yet, these path-based methods primarily focus on local temporal paths appearing in recent times, failing to cap… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.16557v1-abstract-full').style.display = 'inline'; document.getElementById('2412.16557v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.16557v1-abstract-full" style="display: none;"> Reasoning future unknowable facts on temporal knowledge graphs (TKGs) is a challenging task, holding significant academic and practical values for various fields. Existing studies exploring explainable reasoning concentrate on modeling comprehensible temporal paths relevant to the query. Yet, these path-based methods primarily focus on local temporal paths appearing in recent times, failing to capture the complex temporal paths in TKG and resulting in the loss of longer historical relations related to the query. Motivated by the Dual Process Theory in cognitive science, we propose a \textbf{Cogn}itive \textbf{T}emporal \textbf{K}nowledge \textbf{E}xtrapolation framework (CognTKE), which introduces a novel temporal cognitive relation directed graph (TCR-Digraph) and performs interpretable global shallow reasoning and local deep reasoning over the TCR-Digraph. Specifically, the proposed TCR-Digraph is constituted by retrieving significant local and global historical temporal relation paths associated with the query. In addition, CognTKE presents the global shallow reasoner and the local deep reasoner to perform global one-hop temporal relation reasoning (System 1) and local complex multi-hop path reasoning (System 2) over the TCR-Digraph, respectively. The experimental results on four benchmark datasets demonstrate that CognTKE achieves significant improvement in accuracy compared to the state-of-the-art baselines and delivers excellent zero-shot reasoning ability. \textit{The code is available at https://github.com/WeiChen3690/CognTKE}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.16557v1-abstract-full').style.display = 'none'; document.getElementById('2412.16557v1-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 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">AAAI2025 Accept, 12 pages, 9 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.16502">arXiv:2412.16502</a> <span> [<a href="https://arxiv.org/pdf/2412.16502">pdf</a>, <a href="https://arxiv.org/format/2412.16502">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="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> Spatial-Temporal Knowledge Distillation for Takeaway Recommendation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhao%2C+S">Shuyuan Zhao</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+W">Wei Chen</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+B">Boyan Shi</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+L">Liyong Zhou</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+S">Shuohao Lin</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Huaiyu Wan</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="2412.16502v2-abstract-short" style="display: inline;"> The takeaway recommendation system aims to recommend users' future takeaway purchases based on their historical purchase behaviors, thereby improving user satisfaction and boosting merchant sales. Existing methods focus on incorporating auxiliary information or leveraging knowledge graphs to alleviate the sparsity issue of user purchase sequences. However, two main challenges limit the performance… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.16502v2-abstract-full').style.display = 'inline'; document.getElementById('2412.16502v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.16502v2-abstract-full" style="display: none;"> The takeaway recommendation system aims to recommend users' future takeaway purchases based on their historical purchase behaviors, thereby improving user satisfaction and boosting merchant sales. Existing methods focus on incorporating auxiliary information or leveraging knowledge graphs to alleviate the sparsity issue of user purchase sequences. However, two main challenges limit the performance of these approaches: (1) capturing dynamic user preferences on complex geospatial information and (2) efficiently integrating spatial-temporal knowledge from both graphs and sequence data with low computational costs. In this paper, we propose a novel spatial-temporal knowledge distillation model for takeaway recommendation (STKDRec) based on the two-stage training process. Specifically, during the first pre-training stage, a spatial-temporal knowledge graph (STKG) encoder is trained to extract high-order spatial-temporal dependencies and collaborative associations from the STKG. During the second spatial-temporal knowledge distillation (STKD) stage, a spatial-temporal Transformer (ST-Transformer) is employed to comprehensively model dynamic user preferences on various types of fine-grained geospatial information from a sequential perspective. Furthermore, the STKD strategy is introduced to transfer graph-based spatial-temporal knowledge to the ST-Transformer, facilitating the adaptive fusion of rich knowledge derived from both the STKG and sequence data while reducing computational overhead. Extensive experiments on three real-world datasets show that STKDRec significantly outperforms the state-of-the-art baselines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.16502v2-abstract-full').style.display = 'none'; document.getElementById('2412.16502v2-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">v1</span> submitted 21 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 by AAAI2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.05437">arXiv:2412.05437</a> <span> [<a href="https://arxiv.org/pdf/2412.05437">pdf</a>, <a href="https://arxiv.org/format/2412.05437">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> DRL4AOI: A DRL Framework for Semantic-aware AOI Segmentation in Location-Based Services </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Youfang Lin</a>, <a href="/search/cs?searchtype=author&query=Fu%2C+J">Jinji Fu</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+H">Haomin Wen</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jiyuan Wang</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+Z">Zhenjie Wei</a>, <a href="/search/cs?searchtype=author&query=Qiang%2C+Y">Yuting Qiang</a>, <a href="/search/cs?searchtype=author&query=Mao%2C+X">Xiaowei Mao</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+L">Lixia Wu</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+H">Haoyuan Hu</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+Y">Yuxuan Liang</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Huaiyu Wan</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="2412.05437v1-abstract-short" style="display: inline;"> In Location-Based Services (LBS), such as food delivery, a fundamental task is segmenting Areas of Interest (AOIs), aiming at partitioning the urban geographical spaces into non-overlapping regions. Traditional AOI segmentation algorithms primarily rely on road networks to partition urban areas. While promising in modeling the geo-semantics, road network-based models overlooked the service-semanti… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.05437v1-abstract-full').style.display = 'inline'; document.getElementById('2412.05437v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.05437v1-abstract-full" style="display: none;"> In Location-Based Services (LBS), such as food delivery, a fundamental task is segmenting Areas of Interest (AOIs), aiming at partitioning the urban geographical spaces into non-overlapping regions. Traditional AOI segmentation algorithms primarily rely on road networks to partition urban areas. While promising in modeling the geo-semantics, road network-based models overlooked the service-semantic goals (e.g., workload equality) in LBS service. In this paper, we point out that the AOI segmentation problem can be naturally formulated as a Markov Decision Process (MDP), which gradually chooses a nearby AOI for each grid in the current AOI's border. Based on the MDP, we present the first attempt to generalize Deep Reinforcement Learning (DRL) for AOI segmentation, leading to a novel DRL-based framework called DRL4AOI. The DRL4AOI framework introduces different service-semantic goals in a flexible way by treating them as rewards that guide the AOI generation. To evaluate the effectiveness of DRL4AOI, we develop and release an AOI segmentation system. We also present a representative implementation of DRL4AOI - TrajRL4AOI - for AOI segmentation in the logistics service. It introduces a Double Deep Q-learning Network (DDQN) to gradually optimize the AOI generation for two specific semantic goals: i) trajectory modularity, i.e., maximize tightness of the trajectory connections within an AOI and the sparsity of connections between AOIs, ii) matchness with the road network, i.e., maximizing the matchness between AOIs and the road network. Quantitative and qualitative experiments conducted on synthetic and real-world data demonstrate the effectiveness and superiority of our method. The code and system is publicly available at https://github.com/Kogler7/AoiOpt. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.05437v1-abstract-full').style.display = 'none'; document.getElementById('2412.05437v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 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">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/2412.05119">arXiv:2412.05119</a> <span> [<a href="https://arxiv.org/pdf/2412.05119">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> </div> </div> <p class="title is-5 mathjax"> Metamemory: Exploring the Resilience of Older Internal Migrants </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+X">Xiaoxiao Wang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jingjing Zhang</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Huize Wan</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+W">Weiwei Zhang</a>, <a href="/search/cs?searchtype=author&query=Yao%2C+Y">Yuan Yao</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="2412.05119v1-abstract-short" style="display: inline;"> Immigration and aging have always been significant topics of discussion in society, concerning the stability and future development of a country and its people. Research in the field of HCI on immigration and aging has primarily focused on their practical needs but has paid less attention to the adaptability issues of older internal migrants moving with their families. In this study, we investigat… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.05119v1-abstract-full').style.display = 'inline'; document.getElementById('2412.05119v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.05119v1-abstract-full" style="display: none;"> Immigration and aging have always been significant topics of discussion in society, concerning the stability and future development of a country and its people. Research in the field of HCI on immigration and aging has primarily focused on their practical needs but has paid less attention to the adaptability issues of older internal migrants moving with their families. In this study, we investigate the challenges older internal migrants face in adapting socially, using metadata surveys and semi-structured interviews to delve into their life struggles and resilience sources. Our findings highlight the older internal migrants' remarkable resilience, particularly evident in their reminiscences. We explore the integration of reminiscences with the metaverse, identifying the necessary conditions to create a "Metamemory". We introduce a novel design for a metaverse scene that bridges past and present experiences. This aims to encourage discussions on enhancing older internal migrants' reminiscence, leveraging the metaverse's positive potential, and devising strategies to more effectively address older internal migrants' concerns in the future. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.05119v1-abstract-full').style.display = 'none'; document.getElementById('2412.05119v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 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">Journal ref:</span> CHI'2024: Workshop of the CHI Conference on Human Factors in Computing Systems, May 11--16, 2024, Honolulu, HI, USA </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.04733">arXiv:2412.04733</a> <span> [<a href="https://arxiv.org/pdf/2412.04733">pdf</a>, <a href="https://arxiv.org/format/2412.04733">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"> An Experimental Evaluation of Imputation Models for Spatial-Temporal Traffic Data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Guo%2C+S">Shengnan Guo</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+T">Tonglong Wei</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+Y">Yiheng Huang</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+M">Miaomiao Zhao</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+R">Ran Chen</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yan Lin</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Youfang Lin</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Huaiyu Wan</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="2412.04733v1-abstract-short" style="display: inline;"> Traffic data imputation is a critical preprocessing step in intelligent transportation systems, enabling advanced transportation services. Despite significant advancements in this field, selecting the most suitable model for practical applications remains challenging due to three key issues: 1) incomprehensive consideration of missing patterns that describe how data loss along spatial and temporal… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.04733v1-abstract-full').style.display = 'inline'; document.getElementById('2412.04733v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.04733v1-abstract-full" style="display: none;"> Traffic data imputation is a critical preprocessing step in intelligent transportation systems, enabling advanced transportation services. Despite significant advancements in this field, selecting the most suitable model for practical applications remains challenging due to three key issues: 1) incomprehensive consideration of missing patterns that describe how data loss along spatial and temporal dimensions, 2) the lack of test on standardized datasets, and 3) insufficient evaluations. To this end, we first propose practice-oriented taxonomies for missing patterns and imputation models, systematically identifying all possible forms of real-world traffic data loss and analyzing the characteristics of existing models. Furthermore, we introduce a unified benchmarking pipeline to comprehensively evaluate 10 representative models across various missing patterns and rates. This work aims to provide a holistic understanding of traffic data imputation research and serve as a practical guideline. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.04733v1-abstract-full').style.display = 'none'; document.getElementById('2412.04733v1-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 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/2411.17091">arXiv:2411.17091</a> <span> [<a href="https://arxiv.org/pdf/2411.17091">pdf</a>, <a href="https://arxiv.org/format/2411.17091">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> LESS: Efficient Log Storage System Based on Learned Model and Minimum Attribute Tree </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Cheng%2C+Z">Zhiyang Cheng</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Z">Zizhen Zhu</a>, <a href="/search/cs?searchtype=author&query=Dang%2C+H">Haoran Dang</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Hai Wan</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+X">Xibin 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="2411.17091v1-abstract-short" style="display: inline;"> In recent years, cyber attacks have become increasingly sophisticated and persistent. Detection and investigation based on the provenance graph can effectively mitigate cyber intrusion. However, in the long time span of defenses, the sheer size of the provenance graph will pose significant challenges to the storage systems. Faced with long-term storage tasks, existing methods are unable to simulta… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.17091v1-abstract-full').style.display = 'inline'; document.getElementById('2411.17091v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.17091v1-abstract-full" style="display: none;"> In recent years, cyber attacks have become increasingly sophisticated and persistent. Detection and investigation based on the provenance graph can effectively mitigate cyber intrusion. However, in the long time span of defenses, the sheer size of the provenance graph will pose significant challenges to the storage systems. Faced with long-term storage tasks, existing methods are unable to simultaneously achieve lossless information, efficient compression, and fast query support. In this paper, we propose a novel provenance graph storage system, LESS, which consumes smaller storage space and supports faster storage and queries compared to current approaches. We innovatively partition the provenance graph into two distinct components, the graph structure and attribute, and store them separately. Based on their respective characteristics, we devise two appropriate storage schemes: the provenance graph structure storage method based on machine learning and the use of the minimal spanning tree to store the graph attributes. Compared with the state-of-the-art approach, LEONARD, LESS reduces 6.29 times in storage time, while also achieving a 5.24 times reduction in disk usage and an 18.3 times faster query speed while using only 11.5% of the memory on DARPA TC dataset. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.17091v1-abstract-full').style.display = 'none'; document.getElementById('2411.17091v1-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 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/2411.14072">arXiv:2411.14072</a> <span> [<a href="https://arxiv.org/pdf/2411.14072">pdf</a>, <a href="https://arxiv.org/format/2411.14072">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="Programming Languages">cs.PL</span> </div> </div> <p class="title is-5 mathjax"> The Master-Slave Encoder Model for Improving Patent Text Summarization: A New Approach to Combining Specifications and Claims </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhou%2C+S">Shu Zhou</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+X">Xin Wang</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Z">Zhengda Zhou</a>, <a href="/search/cs?searchtype=author&query=Yi%2C+H">Haohan Yi</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+X">Xuhui Zheng</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Hao Wan</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="2411.14072v1-abstract-short" style="display: inline;"> In order to solve the problem of insufficient generation quality caused by traditional patent text abstract generation models only originating from patent specifications, the problem of new terminology OOV caused by rapid patent updates, and the problem of information redundancy caused by insufficient consideration of the high professionalism, accuracy, and uniqueness of patent texts, we proposes… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.14072v1-abstract-full').style.display = 'inline'; document.getElementById('2411.14072v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.14072v1-abstract-full" style="display: none;"> In order to solve the problem of insufficient generation quality caused by traditional patent text abstract generation models only originating from patent specifications, the problem of new terminology OOV caused by rapid patent updates, and the problem of information redundancy caused by insufficient consideration of the high professionalism, accuracy, and uniqueness of patent texts, we proposes a patent text abstract generation model (MSEA) based on a master-slave encoder architecture; Firstly, the MSEA model designs a master-slave encoder, which combines the instructions in the patent text with the claims as input, and fully explores the characteristics and details between the two through the master-slave encoder; Then, the model enhances the consideration of new technical terms in the input sequence based on the pointer network, and further enhances the correlation with the input text by re weighing the "remembered" and "for-gotten" parts of the input sequence from the encoder; Finally, an enhanced repetition suppression mechanism for patent text was introduced to ensure accurate and non redundant abstracts generated. On a publicly available patent text dataset, compared to the state-of-the-art model, Improved Multi-Head Attention Mechanism (IMHAM), the MSEA model achieves an improvement of 0.006, 0.005, and 0.005 in Rouge-1, Rouge-2, and Rouge-L scores, respectively. MSEA leverages the characteristics of patent texts to effectively enhance the quality of patent text generation, demonstrating its advancement and effectiveness in the experiments. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.14072v1-abstract-full').style.display = 'none'; document.getElementById('2411.14072v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 November, 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">25pages, 1 figure</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.00823">arXiv:2411.00823</a> <span> [<a href="https://arxiv.org/pdf/2411.00823">pdf</a>, <a href="https://arxiv.org/format/2411.00823">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> <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"> Mobility-LLM: Learning Visiting Intentions and Travel Preferences from Human Mobility Data with Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gong%2C+L">Letian Gong</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yan Lin</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+X">Xinyue Zhang</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+Y">Yiwen Lu</a>, <a href="/search/cs?searchtype=author&query=Han%2C+X">Xuedi Han</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yichen Liu</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+S">Shengnan Guo</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Youfang Lin</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Huaiyu Wan</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="2411.00823v1-abstract-short" style="display: inline;"> Location-based services (LBS) have accumulated extensive human mobility data on diverse behaviors through check-in sequences. These sequences offer valuable insights into users' intentions and preferences. Yet, existing models analyzing check-in sequences fail to consider the semantics contained in these sequences, which closely reflect human visiting intentions and travel preferences, leading to… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00823v1-abstract-full').style.display = 'inline'; document.getElementById('2411.00823v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.00823v1-abstract-full" style="display: none;"> Location-based services (LBS) have accumulated extensive human mobility data on diverse behaviors through check-in sequences. These sequences offer valuable insights into users' intentions and preferences. Yet, existing models analyzing check-in sequences fail to consider the semantics contained in these sequences, which closely reflect human visiting intentions and travel preferences, leading to an incomplete comprehension. Drawing inspiration from the exceptional semantic understanding and contextual information processing capabilities of large language models (LLMs) across various domains, we present Mobility-LLM, a novel framework that leverages LLMs to analyze check-in sequences for multiple tasks. Since LLMs cannot directly interpret check-ins, we reprogram these sequences to help LLMs comprehensively understand the semantics of human visiting intentions and travel preferences. Specifically, we introduce a visiting intention memory network (VIMN) to capture the visiting intentions at each record, along with a shared pool of human travel preference prompts (HTPP) to guide the LLM in understanding users' travel preferences. These components enhance the model's ability to extract and leverage semantic information from human mobility data effectively. Extensive experiments on four benchmark datasets and three downstream tasks demonstrate that our approach significantly outperforms existing models, underscoring the effectiveness of Mobility-LLM in advancing our understanding of human mobility data within LBS contexts. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00823v1-abstract-full').style.display = 'none'; document.getElementById('2411.00823v1-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> 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">Accepted by NeurIPS2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.22938">arXiv:2410.22938</a> <span> [<a href="https://arxiv.org/pdf/2410.22938">pdf</a>, <a href="https://arxiv.org/format/2410.22938">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</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"> DiffLight: A Partial Rewards Conditioned Diffusion Model for Traffic Signal Control with Missing Data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+H">Hanyang Chen</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+Y">Yang Jiang</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+S">Shengnan Guo</a>, <a href="/search/cs?searchtype=author&query=Mao%2C+X">Xiaowei Mao</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Youfang Lin</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Huaiyu Wan</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="2410.22938v2-abstract-short" style="display: inline;"> The application of reinforcement learning in traffic signal control (TSC) has been extensively researched and yielded notable achievements. However, most existing works for TSC assume that traffic data from all surrounding intersections is fully and continuously available through sensors. In real-world applications, this assumption often fails due to sensor malfunctions or data loss, making TSC wi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.22938v2-abstract-full').style.display = 'inline'; document.getElementById('2410.22938v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.22938v2-abstract-full" style="display: none;"> The application of reinforcement learning in traffic signal control (TSC) has been extensively researched and yielded notable achievements. However, most existing works for TSC assume that traffic data from all surrounding intersections is fully and continuously available through sensors. In real-world applications, this assumption often fails due to sensor malfunctions or data loss, making TSC with missing data a critical challenge. To meet the needs of practical applications, we introduce DiffLight, a novel conditional diffusion model for TSC under data-missing scenarios in the offline setting. Specifically, we integrate two essential sub-tasks, i.e., traffic data imputation and decision-making, by leveraging a Partial Rewards Conditioned Diffusion (PRCD) model to prevent missing rewards from interfering with the learning process. Meanwhile, to effectively capture the spatial-temporal dependencies among intersections, we design a Spatial-Temporal transFormer (STFormer) architecture. In addition, we propose a Diffusion Communication Mechanism (DCM) to promote better communication and control performance under data-missing scenarios. Extensive experiments on five datasets with various data-missing scenarios demonstrate that DiffLight is an effective controller to address TSC with missing data. The code of DiffLight is released at https://github.com/lokol5579/DiffLight-release. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.22938v2-abstract-full').style.display = 'none'; document.getElementById('2410.22938v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 30 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</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.14281">arXiv:2410.14281</a> <span> [<a href="https://arxiv.org/pdf/2410.14281">pdf</a>, <a href="https://arxiv.org/format/2410.14281">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"> PLMTrajRec: A Scalable and Generalizable Trajectory Recovery Method with Pre-trained Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wei%2C+T">Tonglong Wei</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yan Lin</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Youfang Lin</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+S">Shengnan Guo</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+J">Jilin Hu</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+H">Haitao Yuan</a>, <a href="/search/cs?searchtype=author&query=Cong%2C+G">Gao Cong</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Huaiyu Wan</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="2410.14281v2-abstract-short" style="display: inline;"> Spatiotemporal trajectory data is crucial for various applications. However, issues such as device malfunctions and network instability often cause sparse trajectories, leading to lost detailed movement information. Recovering the missing points in sparse trajectories to restore the detailed information is thus essential. Despite recent progress, several challenges remain. First, the lack of large… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.14281v2-abstract-full').style.display = 'inline'; document.getElementById('2410.14281v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.14281v2-abstract-full" style="display: none;"> Spatiotemporal trajectory data is crucial for various applications. However, issues such as device malfunctions and network instability often cause sparse trajectories, leading to lost detailed movement information. Recovering the missing points in sparse trajectories to restore the detailed information is thus essential. Despite recent progress, several challenges remain. First, the lack of large-scale dense trajectory data makes it difficult to train a trajectory recovery model from scratch. Second, the varying spatiotemporal correlations in sparse trajectories make it hard to generalize recovery across different sampling intervals. Third, the lack of location information complicates the extraction of road conditions for missing points. To address these challenges, we propose a novel trajectory recovery model called PLMTrajRec. It leverages the scalability of a pre-trained language model (PLM) and can be fine-tuned with only a limited set of dense trajectories. To handle different sampling intervals in sparse trajectories, we first convert each trajectory's sampling interval and movement features into natural language representations, allowing the PLM to recognize its interval. We then introduce a trajectory encoder to unify trajectories of varying intervals into a single interval and capture their spatiotemporal relationships. To obtain road conditions for missing points, we propose an area flow-guided implicit trajectory prompt, which models road conditions by collecting traffic flows in each region. We also introduce a road condition passing mechanism that uses observed points' road conditions to infer those of the missing points. Experiments on two public trajectory datasets with three sampling intervals each demonstrate the effectiveness, scalability, and generalization ability of PLMTrajRec. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.14281v2-abstract-full').style.display = 'none'; document.getElementById('2410.14281v2-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">v1</span> submitted 18 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/2410.12600">arXiv:2410.12600</a> <span> [<a href="https://arxiv.org/pdf/2410.12600">pdf</a>, <a href="https://arxiv.org/format/2410.12600">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"> On the Risk of Evidence Pollution for Malicious Social Text Detection in the Era of LLMs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wan%2C+H">Herun Wan</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+M">Minnan Luo</a>, <a href="/search/cs?searchtype=author&query=Su%2C+Z">Zhixiong Su</a>, <a href="/search/cs?searchtype=author&query=Dai%2C+G">Guang Dai</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+X">Xiang 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="2410.12600v1-abstract-short" style="display: inline;"> Evidence-enhanced detectors present remarkable abilities in identifying malicious social text with related evidence. However, the rise of large language models (LLMs) brings potential risks of evidence pollution to confuse detectors. This paper explores how to manipulate evidence, simulating potential misuse scenarios including basic pollution, and rephrasing or generating evidence by LLMs. To mit… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.12600v1-abstract-full').style.display = 'inline'; document.getElementById('2410.12600v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.12600v1-abstract-full" style="display: none;"> Evidence-enhanced detectors present remarkable abilities in identifying malicious social text with related evidence. However, the rise of large language models (LLMs) brings potential risks of evidence pollution to confuse detectors. This paper explores how to manipulate evidence, simulating potential misuse scenarios including basic pollution, and rephrasing or generating evidence by LLMs. To mitigate its negative impact, we propose three defense strategies from both the data and model sides, including machine-generated text detection, a mixture of experts, and parameter updating. Extensive experiments on four malicious social text detection tasks with ten datasets present that evidence pollution, especially the generate strategy, significantly compromises existing detectors. On the other hand, the defense strategies could mitigate evidence pollution, but they faced limitations for practical employment, such as the need for annotated data and huge inference costs. Further analysis illustrates that polluted evidence is of high quality, would compromise the model calibration, and could ensemble to amplify the negative impact. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.12600v1-abstract-full').style.display = 'none'; document.getElementById('2410.12600v1-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 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/2410.02406">arXiv:2410.02406</a> <span> [<a href="https://arxiv.org/pdf/2410.02406">pdf</a>, <a href="https://arxiv.org/format/2410.02406">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> ELLMA-T: an Embodied LLM-agent for Supporting English Language Learning in Social VR </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pan%2C+M">Mengxu Pan</a>, <a href="/search/cs?searchtype=author&query=Kitson%2C+A">Alexandra Kitson</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Hongyu Wan</a>, <a href="/search/cs?searchtype=author&query=Prpa%2C+M">Mirjana Prpa</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="2410.02406v1-abstract-short" style="display: inline;"> Many people struggle with learning a new language, with traditional tools falling short in providing contextualized learning tailored to each learner's needs. The recent development of large language models (LLMs) and embodied conversational agents (ECAs) in social virtual reality (VR) provide new opportunities to practice language learning in a contextualized and naturalistic way that takes into… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.02406v1-abstract-full').style.display = 'inline'; document.getElementById('2410.02406v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.02406v1-abstract-full" style="display: none;"> Many people struggle with learning a new language, with traditional tools falling short in providing contextualized learning tailored to each learner's needs. The recent development of large language models (LLMs) and embodied conversational agents (ECAs) in social virtual reality (VR) provide new opportunities to practice language learning in a contextualized and naturalistic way that takes into account the learner's language level and needs. To explore this opportunity, we developed ELLMA-T, an ECA that leverages an LLM (GPT-4) and situated learning framework for supporting learning English language in social VR (VRChat). Drawing on qualitative interviews (N=12), we reveal the potential of ELLMA-T to generate realistic, believable and context-specific role plays for agent-learner interaction in VR, and LLM's capability to provide initial language assessment and continuous feedback to learners. We provide five design implications for the future development of LLM-based language agents in social VR. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.02406v1-abstract-full').style.display = 'none'; document.getElementById('2410.02406v1-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 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">20 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/2410.01098">arXiv:2410.01098</a> <span> [<a href="https://arxiv.org/pdf/2410.01098">pdf</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="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Generative AI Application for Building Industry </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wan%2C+H">Hanlong Wan</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jian Zhang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yan Chen</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+W">Weili Xu</a>, <a href="/search/cs?searchtype=author&query=Feng%2C+F">Fan Feng</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="2410.01098v1-abstract-short" style="display: inline;"> This paper investigates the transformative potential of generative AI technologies, particularly large language models (LLMs), within the building industry. By leveraging these advanced AI tools, the study explores their application across key areas such as energy code compliance, building design optimization, and workforce training. The research highlights how LLMs can automate labor-intensive pr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.01098v1-abstract-full').style.display = 'inline'; document.getElementById('2410.01098v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.01098v1-abstract-full" style="display: none;"> This paper investigates the transformative potential of generative AI technologies, particularly large language models (LLMs), within the building industry. By leveraging these advanced AI tools, the study explores their application across key areas such as energy code compliance, building design optimization, and workforce training. The research highlights how LLMs can automate labor-intensive processes, significantly improving efficiency, accuracy, and safety in building practices. The paper also addresses the challenges associated with interpreting complex visual and textual data in architectural plans and regulatory codes, proposing innovative solutions to enhance AI-driven compliance checking and design processes. Additionally, the study considers the broader implications of AI integration, including the development of AI-powered tools for comprehensive code compliance across various regulatory domains and the potential for AI to revolutionize workforce training through realistic simulations. This paper provides a comprehensive analysis of the current capabilities of generative AI in the building industry while outlining future directions for research and development, aiming to pave the way for smarter, more sustainable, and responsive construction practices. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.01098v1-abstract-full').style.display = 'none'; document.getElementById('2410.01098v1-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 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, 11 figures, 4 tables</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Report number:</span> PNNL-SA-203362 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.17703">arXiv:2409.17703</a> <span> [<a href="https://arxiv.org/pdf/2409.17703">pdf</a>, <a href="https://arxiv.org/format/2409.17703">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"> PGN: The RNN's New Successor is Effective for Long-Range Time Series Forecasting </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jia%2C+Y">Yuxin Jia</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Youfang Lin</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+J">Jing Yu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Shuo Wang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+T">Tianhao Liu</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Huaiyu Wan</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="2409.17703v1-abstract-short" style="display: inline;"> Due to the recurrent structure of RNN, the long information propagation path poses limitations in capturing long-term dependencies, gradient explosion/vanishing issues, and inefficient sequential execution. Based on this, we propose a novel paradigm called Parallel Gated Network (PGN) as the new successor to RNN. PGN directly captures information from previous time steps through the designed Histo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17703v1-abstract-full').style.display = 'inline'; document.getElementById('2409.17703v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.17703v1-abstract-full" style="display: none;"> Due to the recurrent structure of RNN, the long information propagation path poses limitations in capturing long-term dependencies, gradient explosion/vanishing issues, and inefficient sequential execution. Based on this, we propose a novel paradigm called Parallel Gated Network (PGN) as the new successor to RNN. PGN directly captures information from previous time steps through the designed Historical Information Extraction (HIE) layer and leverages gated mechanisms to select and fuse it with the current time step information. This reduces the information propagation path to $\mathcal{O}(1)$, effectively addressing the limitations of RNN. To enhance PGN's performance in long-range time series forecasting tasks, we propose a novel temporal modeling framework called Temporal PGN (TPGN). TPGN incorporates two branches to comprehensively capture the semantic information of time series. One branch utilizes PGN to capture long-term periodic patterns while preserving their local characteristics. The other branch employs patches to capture short-term information and aggregate the global representation of the series. TPGN achieves a theoretical complexity of $\mathcal{O}(\sqrt{L})$, ensuring efficiency in its operations. Experimental results on five benchmark datasets demonstrate the state-of-the-art (SOTA) performance and high efficiency of TPGN, further confirming the effectiveness of PGN as the new successor to RNN in long-range time series forecasting. The code is available in this repository: \url{https://github.com/Water2sea/TPGN}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17703v1-abstract-full').style.display = 'none'; document.getElementById('2409.17703v1-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 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/2409.15623">arXiv:2409.15623</a> <span> [<a href="https://arxiv.org/pdf/2409.15623">pdf</a>, <a href="https://arxiv.org/format/2409.15623">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</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="Sound">cs.SD</span> </div> </div> <p class="title is-5 mathjax"> Safe Guard: an LLM-agent for Real-time Voice-based Hate Speech Detection in Social Virtual Reality </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xu%2C+Y">Yiwen Xu</a>, <a href="/search/cs?searchtype=author&query=Hou%2C+Q">Qinyang Hou</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Hongyu Wan</a>, <a href="/search/cs?searchtype=author&query=Prpa%2C+M">Mirjana Prpa</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="2409.15623v1-abstract-short" style="display: inline;"> In this paper, we present Safe Guard, an LLM-agent for the detection of hate speech in voice-based interactions in social VR (VRChat). Our system leverages Open AI GPT and audio feature extraction for real-time voice interactions. We contribute a system design and evaluation of the system that demonstrates the capability of our approach in detecting hate speech, and reducing false positives compar… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.15623v1-abstract-full').style.display = 'inline'; document.getElementById('2409.15623v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.15623v1-abstract-full" style="display: none;"> In this paper, we present Safe Guard, an LLM-agent for the detection of hate speech in voice-based interactions in social VR (VRChat). Our system leverages Open AI GPT and audio feature extraction for real-time voice interactions. We contribute a system design and evaluation of the system that demonstrates the capability of our approach in detecting hate speech, and reducing false positives compared to currently available approaches. Our results indicate the potential of LLM-based agents in creating safer virtual environments and set the groundwork for further advancements in LLM-driven moderation approaches. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.15623v1-abstract-full').style.display = 'none'; document.getElementById('2409.15623v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.15251">arXiv:2408.15251</a> <span> [<a href="https://arxiv.org/pdf/2408.15251">pdf</a>, <a href="https://arxiv.org/format/2408.15251">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> TrajFM: A Vehicle Trajectory Foundation Model for Region and Task Transferability </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yan Lin</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+T">Tonglong Wei</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Z">Zeyu Zhou</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+H">Haomin Wen</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+J">Jilin Hu</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+S">Shengnan Guo</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Youfang Lin</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Huaiyu Wan</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="2408.15251v1-abstract-short" style="display: inline;"> Vehicle trajectories provide valuable movement information that supports various downstream tasks and powers real-world applications. A desirable trajectory learning model should transfer between different regions and tasks without retraining, thus improving computational efficiency and effectiveness with limited training data. However, a model's ability to transfer across regions is limited by th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.15251v1-abstract-full').style.display = 'inline'; document.getElementById('2408.15251v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.15251v1-abstract-full" style="display: none;"> Vehicle trajectories provide valuable movement information that supports various downstream tasks and powers real-world applications. A desirable trajectory learning model should transfer between different regions and tasks without retraining, thus improving computational efficiency and effectiveness with limited training data. However, a model's ability to transfer across regions is limited by the unique spatial features and POI arrangements of each region, which are closely linked to vehicle movement patterns and difficult to generalize. Additionally, achieving task transferability is challenging due to the differing generation schemes required for various tasks. Existing efforts towards transferability primarily involve learning embedding vectors for trajectories, which perform poorly in region transfer and still require retraining of prediction modules for task transfer. To address these challenges, we propose TrajFM, a vehicle trajectory foundation model that excels in both region and task transferability. For region transferability, we introduce STRFormer as the main learnable model within TrajFM. It integrates spatial, temporal, and POI modalities of trajectories to effectively manage variations in POI arrangements across regions and includes a learnable spatio-temporal Rotary position embedding module for handling spatial features. For task transferability, we propose a trajectory masking and recovery scheme. This scheme unifies the generation processes of various tasks into the masking and recovery of modalities and sub-trajectories, allowing TrajFM to be pre-trained once and transferred to different tasks without retraining. Experiments on two real-world vehicle trajectory datasets under various settings demonstrate the effectiveness of TrajFM. Code is available at https://anonymous.4open.science/r/TrajFM-30E4. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.15251v1-abstract-full').style.display = 'none'; document.getElementById('2408.15251v1-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 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.12809">arXiv:2408.12809</a> <span> [<a href="https://arxiv.org/pdf/2408.12809">pdf</a>, <a href="https://arxiv.org/format/2408.12809">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"> DutyTTE: Deciphering Uncertainty in Origin-Destination Travel Time Estimation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mao%2C+X">Xiaowei Mao</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yan Lin</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+S">Shengnan Guo</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yubin Chen</a>, <a href="/search/cs?searchtype=author&query=Xian%2C+X">Xingyu Xian</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+H">Haomin Wen</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Q">Qisen Xu</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Youfang Lin</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Huaiyu Wan</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="2408.12809v2-abstract-short" style="display: inline;"> Uncertainty quantification in travel time estimation (TTE) aims to estimate the confidence interval for travel time, given the origin (O), destination (D), and departure time (T). Accurately quantifying this uncertainty requires generating the most likely path and assessing travel time uncertainty along the path. This involves two main challenges: 1) Predicting a path that aligns with the ground t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.12809v2-abstract-full').style.display = 'inline'; document.getElementById('2408.12809v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.12809v2-abstract-full" style="display: none;"> Uncertainty quantification in travel time estimation (TTE) aims to estimate the confidence interval for travel time, given the origin (O), destination (D), and departure time (T). Accurately quantifying this uncertainty requires generating the most likely path and assessing travel time uncertainty along the path. This involves two main challenges: 1) Predicting a path that aligns with the ground truth, and 2) modeling the impact of travel time in each segment on overall uncertainty under varying conditions. We propose DutyTTE to address these challenges. For the first challenge, we introduce a deep reinforcement learning method to improve alignment between the predicted path and the ground truth, providing more accurate travel time information from road segments to improve TTE. For the second challenge, we propose a mixture of experts guided uncertainty quantification mechanism to better capture travel time uncertainty for each segment under varying contexts. Additionally, we calibrate our results using Hoeffding's upper-confidence bound to provide statistical guarantees for the estimated confidence intervals. Extensive experiments on two real-world datasets demonstrate the superiority of our proposed method. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.12809v2-abstract-full').style.display = 'none'; document.getElementById('2408.12809v2-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 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 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">7 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.09613">arXiv:2408.09613</a> <span> [<a href="https://arxiv.org/pdf/2408.09613">pdf</a>, <a href="https://arxiv.org/format/2408.09613">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> </div> </div> <p class="title is-5 mathjax"> How Do Social Bots Participate in Misinformation Spread? A Comprehensive Dataset and Analysis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wan%2C+H">Herun Wan</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+M">Minnan Luo</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+Z">Zihan Ma</a>, <a href="/search/cs?searchtype=author&query=Dai%2C+G">Guang Dai</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+X">Xiang 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="2408.09613v1-abstract-short" style="display: inline;"> Information spreads faster through social media platforms than traditional media, thus becoming an ideal medium to spread misinformation. Meanwhile, automated accounts, known as social bots, contribute more to the misinformation dissemination. In this paper, we explore the interplay between social bots and misinformation on the Sina Weibo platform. We propose a comprehensive and large-scale misinf… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.09613v1-abstract-full').style.display = 'inline'; document.getElementById('2408.09613v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.09613v1-abstract-full" style="display: none;"> Information spreads faster through social media platforms than traditional media, thus becoming an ideal medium to spread misinformation. Meanwhile, automated accounts, known as social bots, contribute more to the misinformation dissemination. In this paper, we explore the interplay between social bots and misinformation on the Sina Weibo platform. We propose a comprehensive and large-scale misinformation dataset, containing 11,393 misinformation and 16,416 unbiased real information with multiple modality information, with 952,955 related users. We propose a scalable weak-surprised method to annotate social bots, obtaining 68,040 social bots and 411,635 genuine accounts. To the best of our knowledge, this dataset is the largest dataset containing misinformation and social bots. We conduct comprehensive experiments and analysis on this dataset. Results show that social bots play a central role in misinformation dissemination, participating in news discussions to amplify echo chambers, manipulate public sentiment, and reverse public stances. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.09613v1-abstract-full').style.display = 'none'; document.getElementById('2408.09613v1-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 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.05503">arXiv:2408.05503</a> <span> [<a href="https://arxiv.org/pdf/2408.05503">pdf</a>, <a href="https://arxiv.org/format/2408.05503">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Disentangled Noisy Correspondence Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Dang%2C+Z">Zhuohang Dang</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+M">Minnan Luo</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jihong Wang</a>, <a href="/search/cs?searchtype=author&query=Jia%2C+C">Chengyou Jia</a>, <a href="/search/cs?searchtype=author&query=Han%2C+H">Haochen Han</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Herun Wan</a>, <a href="/search/cs?searchtype=author&query=Dai%2C+G">Guang Dai</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+X">Xiaojun Chang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jingdong Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.05503v1-abstract-short" style="display: inline;"> Cross-modal retrieval is crucial in understanding latent correspondences across modalities. However, existing methods implicitly assume well-matched training data, which is impractical as real-world data inevitably involves imperfect alignments, i.e., noisy correspondences. Although some works explore similarity-based strategies to address such noise, they suffer from sub-optimal similarity predic… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.05503v1-abstract-full').style.display = 'inline'; document.getElementById('2408.05503v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.05503v1-abstract-full" style="display: none;"> Cross-modal retrieval is crucial in understanding latent correspondences across modalities. However, existing methods implicitly assume well-matched training data, which is impractical as real-world data inevitably involves imperfect alignments, i.e., noisy correspondences. Although some works explore similarity-based strategies to address such noise, they suffer from sub-optimal similarity predictions influenced by modality-exclusive information (MEI), e.g., background noise in images and abstract definitions in texts. This issue arises as MEI is not shared across modalities, thus aligning it in training can markedly mislead similarity predictions. Moreover, although intuitive, directly applying previous cross-modal disentanglement methods suffers from limited noise tolerance and disentanglement efficacy. Inspired by the robustness of information bottlenecks against noise, we introduce DisNCL, a novel information-theoretic framework for feature Disentanglement in Noisy Correspondence Learning, to adaptively balance the extraction of MII and MEI with certifiable optimal cross-modal disentanglement efficacy. DisNCL then enhances similarity predictions in modality-invariant subspace, thereby greatly boosting similarity-based alleviation strategy for noisy correspondences. Furthermore, DisNCL introduces soft matching targets to model noisy many-to-many relationships inherent in multi-modal input for noise-robust and accurate cross-modal alignment. Extensive experiments confirm DisNCL's efficacy by 2% average recall improvement. Mutual information estimation and visualization results show that DisNCL learns meaningful MII/MEI subspaces, validating our theoretical analyses. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.05503v1-abstract-full').style.display = 'none'; document.getElementById('2408.05503v1-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 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.04916">arXiv:2408.04916</a> <span> [<a href="https://arxiv.org/pdf/2408.04916">pdf</a>, <a href="https://arxiv.org/format/2408.04916">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"> PTrajM: Efficient and Semantic-rich Trajectory Learning with Pretrained Trajectory-Mamba </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yan Lin</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yichen Liu</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Z">Zeyu Zhou</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+H">Haomin Wen</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+E">Erwen Zheng</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+S">Shengnan Guo</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Youfang Lin</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Huaiyu Wan</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="2408.04916v1-abstract-short" style="display: inline;"> Vehicle trajectories provide crucial movement information for various real-world applications. To better utilize vehicle trajectories, it is essential to develop a trajectory learning approach that can effectively and efficiently extract rich semantic information, including movement behavior and travel purposes, to support accurate downstream applications. However, creating such an approach presen… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.04916v1-abstract-full').style.display = 'inline'; document.getElementById('2408.04916v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.04916v1-abstract-full" style="display: none;"> Vehicle trajectories provide crucial movement information for various real-world applications. To better utilize vehicle trajectories, it is essential to develop a trajectory learning approach that can effectively and efficiently extract rich semantic information, including movement behavior and travel purposes, to support accurate downstream applications. However, creating such an approach presents two significant challenges. First, movement behavior are inherently spatio-temporally continuous, making them difficult to extract efficiently from irregular and discrete trajectory points. Second, travel purposes are related to the functionalities of areas and road segments traversed by vehicles. These functionalities are not available from the raw spatio-temporal trajectory features and are hard to extract directly from complex textual features associated with these areas and road segments. To address these challenges, we propose PTrajM, a novel method capable of efficient and semantic-rich vehicle trajectory learning. To support efficient modeling of movement behavior, we introduce Trajectory-Mamba as the learnable model of PTrajM, which effectively extracts continuous movement behavior while being more computationally efficient than existing structures. To facilitate efficient extraction of travel purposes, we propose a travel purpose-aware pre-training procedure, which enables PTrajM to discern the travel purposes of trajectories without additional computational resources during its embedding process. Extensive experiments on two real-world datasets and comparisons with several state-of-the-art trajectory learning methods demonstrate the effectiveness of PTrajM. Code is available at https://anonymous.4open.science/r/PTrajM-C973. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.04916v1-abstract-full').style.display = 'none'; document.getElementById('2408.04916v1-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 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.04499">arXiv:2408.04499</a> <span> [<a href="https://arxiv.org/pdf/2408.04499">pdf</a>, <a href="https://arxiv.org/format/2408.04499">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"> Knowledge-Aided Semantic Communication Leveraging Probabilistic Graphical Modeling </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wan%2C+H">Haowen Wan</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Q">Qianqian Yang</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jiancheng Tang</a>, <a href="/search/cs?searchtype=author&query=shi%2C+Z">Zhiguo shi</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="2408.04499v1-abstract-short" style="display: inline;"> In this paper, we propose a semantic communication approach based on probabilistic graphical model (PGM). The proposed approach involves constructing a PGM from a training dataset, which is then shared as common knowledge between the transmitter and receiver. We evaluate the importance of various semantic features and present a PGM-based compression algorithm designed to eliminate predictable port… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.04499v1-abstract-full').style.display = 'inline'; document.getElementById('2408.04499v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.04499v1-abstract-full" style="display: none;"> In this paper, we propose a semantic communication approach based on probabilistic graphical model (PGM). The proposed approach involves constructing a PGM from a training dataset, which is then shared as common knowledge between the transmitter and receiver. We evaluate the importance of various semantic features and present a PGM-based compression algorithm designed to eliminate predictable portions of semantic information. Furthermore, we introduce a technique to reconstruct the discarded semantic information at the receiver end, generating approximate results based on the PGM. Simulation results indicate a significant improvement in transmission efficiency over existing methods, while maintaining the quality of the transmitted images. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.04499v1-abstract-full').style.display = 'none'; document.getElementById('2408.04499v1-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 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.18108">arXiv:2407.18108</a> <span> [<a href="https://arxiv.org/pdf/2407.18108">pdf</a>, <a href="https://arxiv.org/format/2407.18108">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="Computers and Society">cs.CY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Physics and Society">physics.soc-ph</span> </div> </div> <p class="title is-5 mathjax"> Graph Neural Ordinary Differential Equations for Coarse-Grained Socioeconomic Dynamics </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Koch%2C+J">James Koch</a>, <a href="/search/cs?searchtype=author&query=Chowdhury%2C+P+R">Pranab Roy Chowdhury</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Heng Wan</a>, <a href="/search/cs?searchtype=author&query=Bhaduri%2C+P">Parin Bhaduri</a>, <a href="/search/cs?searchtype=author&query=Yoon%2C+J">Jim Yoon</a>, <a href="/search/cs?searchtype=author&query=Srikrishnan%2C+V">Vivek Srikrishnan</a>, <a href="/search/cs?searchtype=author&query=Daniel%2C+W+B">W. Brent Daniel</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="2407.18108v1-abstract-short" style="display: inline;"> We present a data-driven machine-learning approach for modeling space-time socioeconomic dynamics. Through coarse-graining fine-scale observations, our modeling framework simplifies these complex systems to a set of tractable mechanistic relationships -- in the form of ordinary differential equations -- while preserving critical system behaviors. This approach allows for expedited 'what if' studie… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.18108v1-abstract-full').style.display = 'inline'; document.getElementById('2407.18108v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.18108v1-abstract-full" style="display: none;"> We present a data-driven machine-learning approach for modeling space-time socioeconomic dynamics. Through coarse-graining fine-scale observations, our modeling framework simplifies these complex systems to a set of tractable mechanistic relationships -- in the form of ordinary differential equations -- while preserving critical system behaviors. This approach allows for expedited 'what if' studies and sensitivity analyses, essential for informed policy-making. Our findings, from a case study of Baltimore, MD, indicate that this machine learning-augmented coarse-grained model serves as a powerful instrument for deciphering the complex interactions between social factors, geography, and exogenous stressors, offering a valuable asset for system forecasting and resilience planning. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.18108v1-abstract-full').style.display = 'none'; document.getElementById('2407.18108v1-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.15899">arXiv:2407.15899</a> <span> [<a href="https://arxiv.org/pdf/2407.15899">pdf</a>, <a href="https://arxiv.org/format/2407.15899">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/TKDE.2024.3434565">10.1109/TKDE.2024.3434565 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Spatial-Temporal Cross-View Contrastive Pre-training for Check-in Sequence Representation Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gong%2C+L">Letian Gong</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Huaiyu Wan</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+S">Shengnan Guo</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xiucheng Li</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yan Lin</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+E">Erwen Zheng</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+T">Tianyi Wang</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Z">Zeyu Zhou</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Youfang Lin</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="2407.15899v3-abstract-short" style="display: inline;"> The rapid growth of location-based services (LBS) has yielded massive amounts of data on human mobility. Effectively extracting meaningful representations for user-generated check-in sequences is pivotal for facilitating various downstream services. However, the user-generated check-in data are simultaneously influenced by the surrounding objective circumstances and the user's subjective intention… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.15899v3-abstract-full').style.display = 'inline'; document.getElementById('2407.15899v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.15899v3-abstract-full" style="display: none;"> The rapid growth of location-based services (LBS) has yielded massive amounts of data on human mobility. Effectively extracting meaningful representations for user-generated check-in sequences is pivotal for facilitating various downstream services. However, the user-generated check-in data are simultaneously influenced by the surrounding objective circumstances and the user's subjective intention. Specifically, the temporal uncertainty and spatial diversity exhibited in check-in data make it difficult to capture the macroscopic spatial-temporal patterns of users and to understand the semantics of user mobility activities. Furthermore, the distinct characteristics of the temporal and spatial information in check-in sequences call for an effective fusion method to incorporate these two types of information. In this paper, we propose a novel Spatial-Temporal Cross-view Contrastive Representation (STCCR) framework for check-in sequence representation learning. Specifically, STCCR addresses the above challenges by employing self-supervision from "spatial topic" and "temporal intention" views, facilitating effective fusion of spatial and temporal information at the semantic level. Besides, STCCR leverages contrastive clustering to uncover users' shared spatial topics from diverse mobility activities, while employing angular momentum contrast to mitigate the impact of temporal uncertainty and noise. We extensively evaluate STCCR on three real-world datasets and demonstrate its superior performance across three downstream tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.15899v3-abstract-full').style.display = 'none'; document.getElementById('2407.15899v3-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <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 has been accepted as a regular paper at IEEE TKDE</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.12550">arXiv:2407.12550</a> <span> [<a href="https://arxiv.org/pdf/2407.12550">pdf</a>, <a href="https://arxiv.org/format/2407.12550">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"> UniTE: A Survey and Unified Pipeline for Pre-training Spatiotemporal Trajectory Embeddings </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yan Lin</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Z">Zeyu Zhou</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yicheng Liu</a>, <a href="/search/cs?searchtype=author&query=Lv%2C+H">Haochen Lv</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+H">Haomin Wen</a>, <a href="/search/cs?searchtype=author&query=Li%2C+T">Tianyi Li</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yushuai Li</a>, <a href="/search/cs?searchtype=author&query=Jensen%2C+C+S">Christian S. Jensen</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+S">Shengnan Guo</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Youfang Lin</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Huaiyu Wan</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="2407.12550v2-abstract-short" style="display: inline;"> Spatiotemporal trajectories are sequences of timestamped locations, which enable a variety of analyses that in turn enable important real-world applications. It is common to map trajectories to vectors, called embeddings, before subsequent analyses. Thus, the qualities of embeddings are very important. Methods for pre-training embeddings, which leverage unlabeled trajectories for training universa… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.12550v2-abstract-full').style.display = 'inline'; document.getElementById('2407.12550v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.12550v2-abstract-full" style="display: none;"> Spatiotemporal trajectories are sequences of timestamped locations, which enable a variety of analyses that in turn enable important real-world applications. It is common to map trajectories to vectors, called embeddings, before subsequent analyses. Thus, the qualities of embeddings are very important. Methods for pre-training embeddings, which leverage unlabeled trajectories for training universal embeddings, have shown promising applicability across different tasks, thus attracting considerable interest. However, research progress on this topic faces two key challenges: a lack of a comprehensive overview of existing methods, resulting in several related methods not being well-recognized, and the absence of a unified pipeline, complicating the development of new methods and the analysis of methods. We present UniTE, a survey and a unified pipeline for this domain. In doing so, we present a comprehensive list of existing methods for pre-training trajectory embeddings, which includes methods that either explicitly or implicitly employ pre-training techniques. Further, we present a unified and modular pipeline with publicly available underlying code, simplifying the process of constructing and evaluating methods for pre-training trajectory embeddings. Additionally, we contribute a selection of experimental results using the proposed pipeline on real-world datasets. Implementation of the pipeline is publicly available at https://github.com/Logan-Lin/UniTE. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.12550v2-abstract-full').style.display = 'none'; document.getElementById('2407.12550v2-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">v1</span> submitted 17 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.09096">arXiv:2407.09096</a> <span> [<a href="https://arxiv.org/pdf/2407.09096">pdf</a>, <a href="https://arxiv.org/format/2407.09096">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"> STD-PLM: Understanding Both Spatial and Temporal Properties of Spatial-Temporal Data with PLM </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Huang%2C+Y">YiHeng Huang</a>, <a href="/search/cs?searchtype=author&query=Mao%2C+X">Xiaowei Mao</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+S">Shengnan Guo</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yubin Chen</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+J">Junfeng Shen</a>, <a href="/search/cs?searchtype=author&query=Li%2C+T">Tiankuo Li</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Youfang Lin</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Huaiyu Wan</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="2407.09096v3-abstract-short" style="display: inline;"> Spatial-temporal forecasting and imputation are important for real-world intelligent systems. Most existing methods are tailored for individual forecasting or imputation tasks but are not designed for both. Additionally, they are less effective for zero-shot and few-shot learning. While pre-trained language model (PLM) have exhibited strong pattern recognition and reasoning abilities across variou… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.09096v3-abstract-full').style.display = 'inline'; document.getElementById('2407.09096v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.09096v3-abstract-full" style="display: none;"> Spatial-temporal forecasting and imputation are important for real-world intelligent systems. Most existing methods are tailored for individual forecasting or imputation tasks but are not designed for both. Additionally, they are less effective for zero-shot and few-shot learning. While pre-trained language model (PLM) have exhibited strong pattern recognition and reasoning abilities across various tasks, including few-shot and zero-shot learning, their applications in spatial-temporal data understanding has been constrained by insufficient modeling of complex correlations such as the temporal correlations, spatial connectivity, non-pairwise and high-order spatial-temporal correlations within data. In this paper, we propose STD-PLM for understanding both spatial and temporal properties of \underline{S}patial-\underline{T}emporal \underline{D}ata with \underline{PLM}, which is capable of implementing both spatial-temporal forecasting and imputation tasks. STD-PLM understands spatial-temporal correlations via explicitly designed spatial and temporal tokenizers. Topology-aware node embeddings are designed for PLM to comprehend and exploit the topology structure of data in inductive manner. Furthermore, to mitigate the efficiency issues introduced by the PLM, we design a sandglass attention module (SGA) combined with a specific constrained loss function, which significantly improves the model's efficiency while ensuring performance. Extensive experiments demonstrate that STD-PLM exhibits competitive performance and generalization capabilities across the forecasting and imputation tasks on various datasets. Moreover, STD-PLM achieves promising results on both few-shot and zero-shot tasks.The code is made available at \href{https://anonymous.4open.science/r/STD-PLM-F3BA}{https://anonymous.4open.science/r/STD-PLM-F3BA} <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.09096v3-abstract-full').style.display = 'none'; document.getElementById('2407.09096v3-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 12 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.20015">arXiv:2406.20015</a> <span> [<a href="https://arxiv.org/pdf/2406.20015">pdf</a>, <a href="https://arxiv.org/format/2406.20015">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"> ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yuxiang Zhang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+J">Jing Chen</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Junjie Wang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yaxin Liu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+C">Cheng Yang</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+C">Chufan Shi</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+X">Xinyu Zhu</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Z">Zihao Lin</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Hanwen Wan</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Y">Yujiu Yang</a>, <a href="/search/cs?searchtype=author&query=Sakai%2C+T">Tetsuya Sakai</a>, <a href="/search/cs?searchtype=author&query=Feng%2C+T">Tian Feng</a>, <a href="/search/cs?searchtype=author&query=Yamana%2C+H">Hayato Yamana</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.20015v2-abstract-short" style="display: inline;"> Tool-augmented large language models (LLMs) are rapidly being integrated into real-world applications. Due to the lack of benchmarks, the community has yet to fully understand the hallucination issues within these models. To address this challenge, we introduce a comprehensive diagnostic benchmark, ToolBH. Specifically, we assess the LLM's hallucinations through two perspectives: depth and breadth… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.20015v2-abstract-full').style.display = 'inline'; document.getElementById('2406.20015v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.20015v2-abstract-full" style="display: none;"> Tool-augmented large language models (LLMs) are rapidly being integrated into real-world applications. Due to the lack of benchmarks, the community has yet to fully understand the hallucination issues within these models. To address this challenge, we introduce a comprehensive diagnostic benchmark, ToolBH. Specifically, we assess the LLM's hallucinations through two perspectives: depth and breadth. In terms of depth, we propose a multi-level diagnostic process, including (1) solvability detection, (2) solution planning, and (3) missing-tool analysis. For breadth, we consider three scenarios based on the characteristics of the toolset: missing necessary tools, potential tools, and limited functionality tools. Furthermore, we developed seven tasks and collected 700 evaluation samples through multiple rounds of manual annotation. The results show the significant challenges presented by the ToolBH benchmark. The current advanced models Gemini-1.5-Pro and GPT-4o only achieve total scores of 45.3 and 37.0, respectively, on a scale of 100. In this benchmark, larger model parameters do not guarantee better performance; the training data and response strategies also play crucial roles in tool-enhanced LLM scenarios. Our diagnostic analysis indicates that the primary reason for model errors lies in assessing task solvability. Additionally, open-weight models suffer from performance drops with verbose replies, whereas proprietary models excel with longer reasoning. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.20015v2-abstract-full').style.display = 'none'; document.getElementById('2406.20015v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 28 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.00734">arXiv:2406.00734</a> <span> [<a href="https://arxiv.org/pdf/2406.00734">pdf</a>, <a href="https://arxiv.org/format/2406.00734">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"> GLADformer: A Mixed Perspective for Graph-level Anomaly Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xu%2C+F">Fan Xu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+N">Nan Wang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+H">Hao Wu</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+X">Xuezhi Wen</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+D">Dalin Zhang</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+S">Siyang Lu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+B">Binyong Li</a>, <a href="/search/cs?searchtype=author&query=Gong%2C+W">Wei Gong</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Hai Wan</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+X">Xibin 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="2406.00734v2-abstract-short" style="display: inline;"> Graph-Level Anomaly Detection (GLAD) aims to distinguish anomalous graphs within a graph dataset. However, current methods are constrained by their receptive fields, struggling to learn global features within the graphs. Moreover, most contemporary methods are based on spatial domain and lack exploration of spectral characteristics. In this paper, we propose a multi-perspective hybrid graph-level… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.00734v2-abstract-full').style.display = 'inline'; document.getElementById('2406.00734v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.00734v2-abstract-full" style="display: none;"> Graph-Level Anomaly Detection (GLAD) aims to distinguish anomalous graphs within a graph dataset. However, current methods are constrained by their receptive fields, struggling to learn global features within the graphs. Moreover, most contemporary methods are based on spatial domain and lack exploration of spectral characteristics. In this paper, we propose a multi-perspective hybrid graph-level anomaly detector namely GLADformer, consisting of two key modules. Specifically, we first design a Graph Transformer module with global spectrum enhancement, which ensures balanced and resilient parameter distributions by fusing global features and spectral distribution characteristics. Furthermore, to uncover local anomalous attributes, we customize a band-pass spectral GNN message passing module that further enhances the model's generalization capability. Through comprehensive experiments on ten real-world datasets from multiple domains, we validate the effectiveness and robustness of GLADformer. This demonstrates that GLADformer outperforms current state-of-the-art models in graph-level anomaly detection, particularly in effectively capturing global anomaly representations and spectral characteristics. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.00734v2-abstract-full').style.display = 'none'; document.getElementById('2406.00734v2-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 2 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.12459">arXiv:2405.12459</a> <span> [<a href="https://arxiv.org/pdf/2405.12459">pdf</a>, <a href="https://arxiv.org/format/2405.12459">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"> TrajCogn: Leveraging LLMs for Cognizing Movement Patterns and Travel Purposes from Trajectories </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhou%2C+Z">Zeyu Zhou</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yan Lin</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+H">Haomin Wen</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Q">Qisen Xu</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+S">Shengnan Guo</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+J">Jilin Hu</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Youfang Lin</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Huaiyu Wan</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2405.12459v2-abstract-short" style="display: inline;"> Spatio-temporal trajectories are crucial in various data mining tasks. It is important to develop a versatile trajectory learning method that performs different tasks with high accuracy. This involves effectively extracting two core aspects of information--movement patterns and travel purposes--from trajectories. However, this is challenging due to limitations in model capacity and the quality and… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.12459v2-abstract-full').style.display = 'inline'; document.getElementById('2405.12459v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.12459v2-abstract-full" style="display: none;"> Spatio-temporal trajectories are crucial in various data mining tasks. It is important to develop a versatile trajectory learning method that performs different tasks with high accuracy. This involves effectively extracting two core aspects of information--movement patterns and travel purposes--from trajectories. However, this is challenging due to limitations in model capacity and the quality and scale of trajectory datasets. Meanwhile, large language models (LLMs) have shown great success in versatility by training on large-scale, high-quality datasets. Given the similarities between trajectories and sentences, there's potential to leverage LLMs to develop an effective trajectory learning method. However, standard LLMs are not designed to handle the unique spatio-temporal features of trajectories and cannot extract movement patterns and travel purposes. To address these challenges, we propose a model called TrajCogn that effectively utilizes LLMs to model trajectories. TrajCogn leverages the strengths of LLMs to create a versatile trajectory learning approach while addressing the limitations of standard LLMs. First, TrajCogn incorporates a novel trajectory semantic embedder that enables LLMs to process spatio-temporal features and extract movement patterns and travel purposes. Second, TrajCogn introduces a new trajectory prompt that integrates these patterns and purposes into LLMs, allowing the model to adapt to various tasks. Extensive experiments on two real-world datasets and two representative tasks demonstrate that TrajCogn successfully achieves its design goals. Codes are available at https://anonymous.4open.science/r/TrajCogn-5021. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.12459v2-abstract-full').style.display = 'none'; document.getElementById('2405.12459v2-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 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.19141">arXiv:2404.19141</a> <span> [<a href="https://arxiv.org/pdf/2404.19141">pdf</a>, <a href="https://arxiv.org/format/2404.19141">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"> Micro-Macro Spatial-Temporal Graph-based Encoder-Decoder for Map-Constrained Trajectory Recovery </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wei%2C+T">Tonglong Wei</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Youfang Lin</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yan Lin</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+S">Shengnan Guo</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+L">Lan Zhang</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Huaiyu Wan</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.19141v1-abstract-short" style="display: inline;"> Recovering intermediate missing GPS points in a sparse trajectory, while adhering to the constraints of the road network, could offer deep insights into users' moving behaviors in intelligent transportation systems. Although recent studies have demonstrated the advantages of achieving map-constrained trajectory recovery via an end-to-end manner, they still face two significant challenges. Firstly,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.19141v1-abstract-full').style.display = 'inline'; document.getElementById('2404.19141v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.19141v1-abstract-full" style="display: none;"> Recovering intermediate missing GPS points in a sparse trajectory, while adhering to the constraints of the road network, could offer deep insights into users' moving behaviors in intelligent transportation systems. Although recent studies have demonstrated the advantages of achieving map-constrained trajectory recovery via an end-to-end manner, they still face two significant challenges. Firstly, existing methods are mostly sequence-based models. It is extremely hard for them to comprehensively capture the micro-semantics of individual trajectory, including the information of each GPS point and the movement between two GPS points. Secondly, existing approaches ignore the impact of the macro-semantics, i.e., the road conditions and the people's shared travel preferences reflected by a group of trajectories. To address the above challenges, we propose a Micro-Macro Spatial-Temporal Graph-based Encoder-Decoder (MM-STGED). Specifically, we model each trajectory as a graph to efficiently describe the micro-semantics of trajectory and design a novel message-passing mechanism to learn trajectory representations. Additionally, we extract the macro-semantics of trajectories and further incorporate them into a well-designed graph-based decoder to guide trajectory recovery. Extensive experiments conducted on sparse trajectories with three different sampling intervals that are respectively constructed from two real-world trajectory datasets demonstrate the superiority of our proposed model. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.19141v1-abstract-full').style.display = 'none'; document.getElementById('2404.19141v1-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 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">This paper has been accepted as a regular paper at IEEE TKDE</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.11432">arXiv:2403.11432</a> <span> [<a href="https://arxiv.org/pdf/2403.11432">pdf</a>, <a href="https://arxiv.org/format/2403.11432">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="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"> Demystifying the Physics of Deep Reinforcement Learning-Based Autonomous Vehicle Decision-Making </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wan%2C+H">Hanxi Wan</a>, <a href="/search/cs?searchtype=author&query=Li%2C+P">Pei Li</a>, <a href="/search/cs?searchtype=author&query=Kusari%2C+A">Arpan Kusari</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.11432v2-abstract-short" style="display: inline;"> With the advent of universal function approximators in the domain of reinforcement learning, the number of practical applications leveraging deep reinforcement learning (DRL) has exploded. Decision-making in autonomous vehicles (AVs) has emerged as a chief application among them, taking the sensor data or the higher-order kinematic variables as the input and providing a discrete choice or continuo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.11432v2-abstract-full').style.display = 'inline'; document.getElementById('2403.11432v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.11432v2-abstract-full" style="display: none;"> With the advent of universal function approximators in the domain of reinforcement learning, the number of practical applications leveraging deep reinforcement learning (DRL) has exploded. Decision-making in autonomous vehicles (AVs) has emerged as a chief application among them, taking the sensor data or the higher-order kinematic variables as the input and providing a discrete choice or continuous control output. There has been a continuous effort to understand the black-box nature of the DRL models, but so far, there hasn't been any discussion (to the best of authors' knowledge) about how the models learn the physical process. This presents an overwhelming limitation that restricts the real-world deployment of DRL in AVs. Therefore, in this research work, we try to decode the knowledge learnt by the attention-based DRL framework about the physical process. We use a continuous proximal policy optimization-based DRL algorithm as the baseline model and add a multi-head attention framework in an open-source AV simulation environment. We provide some analytical techniques for discussing the interpretability of the trained models in terms of explainability and causality for spatial and temporal correlations. We show that the weights in the first head encode the positions of the neighboring vehicles while the second head focuses on the leader vehicle exclusively. Also, the ego vehicle's action is causally dependent on the vehicles in the target lane spatially and temporally. Through these findings, we reliably show that these techniques can help practitioners decipher the results of the DRL algorithms. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.11432v2-abstract-full').style.display = 'none'; document.getElementById('2403.11432v2-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 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 17 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Submitted for peer-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/2403.09733">arXiv:2403.09733</a> <span> [<a href="https://arxiv.org/pdf/2403.09733">pdf</a>, <a href="https://arxiv.org/format/2403.09733">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"> OverleafCopilot: Empowering Academic Writing in Overleaf with Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wen%2C+H">Haomin Wen</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+Z">Zhenjie Wei</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yan Lin</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jiyuan Wang</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+Y">Yuxuan Liang</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Huaiyu Wan</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.09733v1-abstract-short" style="display: inline;"> The rapid development of Large Language Models (LLMs) has facilitated a variety of applications from different domains. In this technical report, we explore the integration of LLMs and the popular academic writing tool, Overleaf, to enhance the efficiency and quality of academic writing. To achieve the above goal, there are three challenges: i) including seamless interaction between Overleaf and L… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.09733v1-abstract-full').style.display = 'inline'; document.getElementById('2403.09733v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.09733v1-abstract-full" style="display: none;"> The rapid development of Large Language Models (LLMs) has facilitated a variety of applications from different domains. In this technical report, we explore the integration of LLMs and the popular academic writing tool, Overleaf, to enhance the efficiency and quality of academic writing. To achieve the above goal, there are three challenges: i) including seamless interaction between Overleaf and LLMs, ii) establishing reliable communication with the LLM provider, and iii) ensuring user privacy. To address these challenges, we present OverleafCopilot, the first-ever tool (i.e., a browser extension) that seamlessly integrates LLMs and Overleaf, enabling researchers to leverage the power of LLMs while writing papers. Specifically, we first propose an effective framework to bridge LLMs and Overleaf. Then, we developed PromptGenius, a website for researchers to easily find and share high-quality up-to-date prompts. Thirdly, we propose an agent command system to help researchers quickly build their customizable agents. OverleafCopilot (https://chromewebstore.google.com/detail/overleaf-copilot/eoadabdpninlhkkbhngoddfjianhlghb ) has been on the Chrome Extension Store, which now serves thousands of researchers. Additionally, the code of PromptGenius is released at https://github.com/wenhaomin/ChatGPT-PromptGenius. We believe our work has the potential to revolutionize academic writing practices, empowering researchers to produce higher-quality papers in less time. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.09733v1-abstract-full').style.display = 'none'; document.getElementById('2403.09733v1-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 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.05268">arXiv:2403.05268</a> <span> [<a href="https://arxiv.org/pdf/2403.05268">pdf</a>, <a href="https://arxiv.org/ps/2403.05268">ps</a>, <a href="https://arxiv.org/format/2403.05268">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Deep Prompt Multi-task Network for Abuse Language Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhu%2C+J">Jian Zhu</a>, <a href="/search/cs?searchtype=author&query=Ruan%2C+Y">Yuping Ruan</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+J">Jingfei Chang</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+W">Wenhui Sun</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Hui Wan</a>, <a href="/search/cs?searchtype=author&query=Long%2C+J">Jian Long</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+C">Cheng Luo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.05268v2-abstract-short" style="display: inline;"> The detection of abusive language remains a long-standing challenge with the extensive use of social networks. The detection task of abusive language suffers from limited accuracy. We argue that the existing detection methods utilize the fine-tuning technique of the pre-trained language models (PLMs) to handle downstream tasks. Hence, these methods fail to stimulate the general knowledge of the PL… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.05268v2-abstract-full').style.display = 'inline'; document.getElementById('2403.05268v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.05268v2-abstract-full" style="display: none;"> The detection of abusive language remains a long-standing challenge with the extensive use of social networks. The detection task of abusive language suffers from limited accuracy. We argue that the existing detection methods utilize the fine-tuning technique of the pre-trained language models (PLMs) to handle downstream tasks. Hence, these methods fail to stimulate the general knowledge of the PLMs. To address the problem, we propose a novel Deep Prompt Multi-task Network (DPMN) for abuse language detection. Specifically, DPMN first attempts to design two forms of deep prompt tuning and light prompt tuning for the PLMs. The effects of different prompt lengths, tuning strategies, and prompt initialization methods on detecting abusive language are studied. In addition, we propose a Task Head based on Bi-LSTM and FFN, which can be used as a short text classifier. Eventually, DPMN utilizes multi-task learning to improve detection metrics further. The multi-task network has the function of transferring effective knowledge. The proposed DPMN is evaluated against eight typical methods on three public datasets: OLID, SOLID, and AbuseAnalyzer. The experimental results show that our DPMN outperforms the state-of-the-art methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.05268v2-abstract-full').style.display = 'none'; document.getElementById('2403.05268v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 8 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by the International Conference on Pattern Recognition (ICPR) 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.10426">arXiv:2402.10426</a> <span> [<a href="https://arxiv.org/pdf/2402.10426">pdf</a>, <a href="https://arxiv.org/format/2402.10426">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"> DELL: Generating Reactions and Explanations for LLM-Based Misinformation Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wan%2C+H">Herun Wan</a>, <a href="/search/cs?searchtype=author&query=Feng%2C+S">Shangbin Feng</a>, <a href="/search/cs?searchtype=author&query=Tan%2C+Z">Zhaoxuan Tan</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+H">Heng Wang</a>, <a href="/search/cs?searchtype=author&query=Tsvetkov%2C+Y">Yulia Tsvetkov</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+M">Minnan Luo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.10426v2-abstract-short" style="display: inline;"> Large language models are limited by challenges in factuality and hallucinations to be directly employed off-the-shelf for judging the veracity of news articles, where factual accuracy is paramount. In this work, we propose DELL that identifies three key stages in misinformation detection where LLMs could be incorporated as part of the pipeline: 1) LLMs could \emph{generate news reactions} to repr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.10426v2-abstract-full').style.display = 'inline'; document.getElementById('2402.10426v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.10426v2-abstract-full" style="display: none;"> Large language models are limited by challenges in factuality and hallucinations to be directly employed off-the-shelf for judging the veracity of news articles, where factual accuracy is paramount. In this work, we propose DELL that identifies three key stages in misinformation detection where LLMs could be incorporated as part of the pipeline: 1) LLMs could \emph{generate news reactions} to represent diverse perspectives and simulate user-news interaction networks; 2) LLMs could \emph{generate explanations} for proxy tasks (e.g., sentiment, stance) to enrich the contexts of news articles and produce experts specializing in various aspects of news understanding; 3) LLMs could \emph{merge task-specific experts} and provide an overall prediction by incorporating the predictions and confidence scores of varying experts. Extensive experiments on seven datasets with three LLMs demonstrate that DELL outperforms state-of-the-art baselines by up to 16.8\% in macro f1-score. Further analysis reveals that the generated reactions and explanations are greatly helpful in misinformation detection, while our proposed LLM-guided expert merging helps produce better-calibrated predictions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.10426v2-abstract-full').style.display = 'none'; document.getElementById('2402.10426v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.07369">arXiv:2402.07369</a> <span> [<a href="https://arxiv.org/pdf/2402.07369">pdf</a>, <a href="https://arxiv.org/format/2402.07369">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"> Diff-RNTraj: A Structure-aware Diffusion Model for Road Network-constrained Trajectory Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wei%2C+T">Tonglong Wei</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Youfang Lin</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+S">Shengnan Guo</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yan Lin</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+Y">Yiheng Huang</a>, <a href="/search/cs?searchtype=author&query=Xiang%2C+C">Chenyang Xiang</a>, <a href="/search/cs?searchtype=author&query=Bai%2C+Y">Yuqing Bai</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Huaiyu Wan</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.07369v2-abstract-short" style="display: inline;"> Trajectory data is essential for various applications as it records the movement of vehicles. However, publicly available trajectory datasets remain limited in scale due to privacy concerns, which hinders the development of trajectory data mining and trajectory-based applications. To address this issue, some methods for generating synthetic trajectories have been proposed to expand the scale of th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.07369v2-abstract-full').style.display = 'inline'; document.getElementById('2402.07369v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.07369v2-abstract-full" style="display: none;"> Trajectory data is essential for various applications as it records the movement of vehicles. However, publicly available trajectory datasets remain limited in scale due to privacy concerns, which hinders the development of trajectory data mining and trajectory-based applications. To address this issue, some methods for generating synthetic trajectories have been proposed to expand the scale of the dataset. However, all existing methods generate trajectories in the geographical coordinate system, which poses two limitations for their utilization in practical applications: 1) the inability to ensure that the generated trajectories are constrained on the road. 2) the lack of road-related information. In this paper, we propose a new problem to meet the practical application need, \emph{i.e.}, road network-constrained trajectory (RNTraj) generation, which can directly generate trajectories on the road network with road-related information. RNTraj is a hybrid type of data, in which each point is represented by a discrete road segment and a continuous moving rate. To generate RNTraj, we design a diffusion model called Diff-RNTraj. This model can effectively handle the hybrid RNTraj using a continuous diffusion framework by incorporating a pre-training strategy to embed hybrid RNTraj into continuous representations. During the sampling stage, a RNTraj decoder is designed to map the continuous representation generated by the diffusion model back to the hybrid RNTraj format. Furthermore, Diff-RNTraj introduces a novel loss function to enhance the spatial validity of the generated trajectories. Extensive experiments conducted on two real-world trajectory datasets demonstrate the effectiveness of the proposed model. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.07369v2-abstract-full').style.display = 'none'; document.getElementById('2402.07369v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 11 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">This paper has been accepted as a regular paper at IEEE TKDE</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.07232">arXiv:2402.07232</a> <span> [<a href="https://arxiv.org/pdf/2402.07232">pdf</a>, <a href="https://arxiv.org/format/2402.07232">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"> UVTM: Universal Vehicle Trajectory Modeling with ST Feature Domain Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yan Lin</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+J">Jilin Hu</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+S">Shengnan Guo</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+B">Bin Yang</a>, <a href="/search/cs?searchtype=author&query=Jensen%2C+C+S">Christian S. Jensen</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Youfang Lin</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Huaiyu Wan</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.07232v3-abstract-short" style="display: inline;"> Vehicle movement is frequently captured in the form of trajectories, i.e., sequences of timestamped locations. Numerous methods exist that target different tasks involving trajectories such as travel-time estimation, trajectory recovery, and trajectory prediction. However, most methods target only one specific task and cannot be applied universally. Existing efforts to create a universal trajector… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.07232v3-abstract-full').style.display = 'inline'; document.getElementById('2402.07232v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.07232v3-abstract-full" style="display: none;"> Vehicle movement is frequently captured in the form of trajectories, i.e., sequences of timestamped locations. Numerous methods exist that target different tasks involving trajectories such as travel-time estimation, trajectory recovery, and trajectory prediction. However, most methods target only one specific task and cannot be applied universally. Existing efforts to create a universal trajectory model often involve adding prediction modules for adapting to different tasks, while also struggle with incomplete or sparse trajectories. To address these shortcomings, we propose the Universal Vehicle Trajectory Model (UVTM) designed to support different tasks based on incomplete or sparse trajectories without the need for retraining or extra prediction modules. To addresses task adaptability on incomplete trajectories, UVTM divide the spatio-temporal features of trajectories into three distinct domains. Each domain can be masked and generated independently to suit the input and output needs of specific tasks. To handle sparse trajectories effectively, UVTM is pre-trained by reconstructing densely sampled trajectories from sparsely sampled ones, allowing it to extract detailed spatio-temporal information from sparse trajectories. Experiments involving three representative trajectory-related tasks on two real-world vehicle trajectory datasets provide insight into the intended properties performance of UVTM and offer evidence that UVTM is capable of meeting its objectives. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.07232v3-abstract-full').style.display = 'none'; document.getElementById('2402.07232v3-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 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 11 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.04454">arXiv:2402.04454</a> <span> [<a href="https://arxiv.org/pdf/2402.04454">pdf</a>, <a href="https://arxiv.org/format/2402.04454">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> </div> </div> <p class="title is-5 mathjax"> Evolving Mobile Cloud Gaming with 5G Standalone Network Telemetry </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wan%2C+H">Haoran Wan</a>, <a href="/search/cs?searchtype=author&query=Jamieson%2C+K">Kyle Jamieson</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.04454v2-abstract-short" style="display: inline;"> Mobile cloud gaming places the simultaneous demands of high capacity and low latency on the wireless network, demands that Private and Metropolitan-Area Standalone 5G networks are poised to meet. However, lacking introspection into the 5G Radio Access Network (RAN), cloud gaming servers are ill-poised to cope with the vagaries of the wireless last hop to a mobile client, while 5G network operators… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.04454v2-abstract-full').style.display = 'inline'; document.getElementById('2402.04454v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.04454v2-abstract-full" style="display: none;"> Mobile cloud gaming places the simultaneous demands of high capacity and low latency on the wireless network, demands that Private and Metropolitan-Area Standalone 5G networks are poised to meet. However, lacking introspection into the 5G Radio Access Network (RAN), cloud gaming servers are ill-poised to cope with the vagaries of the wireless last hop to a mobile client, while 5G network operators run mostly closed networks, limiting their potential for co-design with the wider internet and user applications. This paper presents Telesa, a passive, incrementally-deployable, and independently-deployable Standalone 5G network telemetry system that streams fine-grained RAN capacity, latency, and retransmission information to application servers to enable better millisecond scale, application-level decisions on offered load and bit rate adaptation than end-to-end latency measurements or end-to-end packet losses currently permit. We design, implement, and evaluate a Telesa telemetry-enhanced game streaming platform, demonstrating exact congestion-control that can better adapt game video bitrate while simultaneously controlling end-to-end latency, thus maximizing game quality of experience. Our experimental evaluation on a production 5G Standalone network demonstrates a 178-249% Quality of Experience improvement versus two state-of-the-art cloud gaming applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.04454v2-abstract-full').style.display = 'none'; document.getElementById('2402.04454v2-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 6 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.00371">arXiv:2402.00371</a> <span> [<a href="https://arxiv.org/pdf/2402.00371">pdf</a>, <a href="https://arxiv.org/format/2402.00371">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"> What Does the Bot Say? Opportunities and Risks of Large Language Models in Social Media Bot Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Feng%2C+S">Shangbin Feng</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Herun Wan</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+N">Ningnan Wang</a>, <a href="/search/cs?searchtype=author&query=Tan%2C+Z">Zhaoxuan Tan</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+M">Minnan Luo</a>, <a href="/search/cs?searchtype=author&query=Tsvetkov%2C+Y">Yulia Tsvetkov</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.00371v2-abstract-short" style="display: inline;"> Social media bot detection has always been an arms race between advancements in machine learning bot detectors and adversarial bot strategies to evade detection. In this work, we bring the arms race to the next level by investigating the opportunities and risks of state-of-the-art large language models (LLMs) in social bot detection. To investigate the opportunities, we design novel LLM-based bot… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.00371v2-abstract-full').style.display = 'inline'; document.getElementById('2402.00371v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.00371v2-abstract-full" style="display: none;"> Social media bot detection has always been an arms race between advancements in machine learning bot detectors and adversarial bot strategies to evade detection. In this work, we bring the arms race to the next level by investigating the opportunities and risks of state-of-the-art large language models (LLMs) in social bot detection. To investigate the opportunities, we design novel LLM-based bot detectors by proposing a mixture-of-heterogeneous-experts framework to divide and conquer diverse user information modalities. To illuminate the risks, we explore the possibility of LLM-guided manipulation of user textual and structured information to evade detection. Extensive experiments with three LLMs on two datasets demonstrate that instruction tuning on merely 1,000 annotated examples produces specialized LLMs that outperform state-of-the-art baselines by up to 9.1% on both datasets, while LLM-guided manipulation strategies could significantly bring down the performance of existing bot detectors by up to 29.6% and harm the calibration and reliability of bot detection systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.00371v2-abstract-full').style.display = 'none'; document.getElementById('2402.00371v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 1 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">ACL 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/2401.17188">arXiv:2401.17188</a> <span> [<a href="https://arxiv.org/pdf/2401.17188">pdf</a>, <a href="https://arxiv.org/format/2401.17188">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Nested Construction of Polar Codes via Transformers </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ankireddy%2C+S+K">Sravan Kumar Ankireddy</a>, <a href="/search/cs?searchtype=author&query=Hebbar%2C+S+A">S Ashwin Hebbar</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Heping Wan</a>, <a href="/search/cs?searchtype=author&query=Cho%2C+J">Joonyoung Cho</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Charlie Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2401.17188v1-abstract-short" style="display: inline;"> Tailoring polar code construction for decoding algorithms beyond successive cancellation has remained a topic of significant interest in the field. However, despite the inherent nested structure of polar codes, the use of sequence models in polar code construction is understudied. In this work, we propose using a sequence modeling framework to iteratively construct a polar code for any given lengt… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.17188v1-abstract-full').style.display = 'inline'; document.getElementById('2401.17188v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.17188v1-abstract-full" style="display: none;"> Tailoring polar code construction for decoding algorithms beyond successive cancellation has remained a topic of significant interest in the field. However, despite the inherent nested structure of polar codes, the use of sequence models in polar code construction is understudied. In this work, we propose using a sequence modeling framework to iteratively construct a polar code for any given length and rate under various channel conditions. Simulations show that polar codes designed via sequential modeling using transformers outperform both 5G-NR sequence and Density Evolution based approaches for both AWGN and Rayleigh fading channels. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.17188v1-abstract-full').style.display = 'none'; document.getElementById('2401.17188v1-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, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">7 pages; 8 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.06441">arXiv:2312.06441</a> <span> [<a href="https://arxiv.org/pdf/2312.06441">pdf</a>, <a href="https://arxiv.org/format/2312.06441">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> </div> </div> <p class="title is-5 mathjax"> Revisiting Graph-Based Fraud Detection in Sight of Heterophily and Spectrum </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xu%2C+F">Fan Xu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+N">Nan Wang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+H">Hao Wu</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+X">Xuezhi Wen</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+X">Xibin Zhao</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Hai Wan</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2312.06441v3-abstract-short" style="display: inline;"> Graph-based fraud detection (GFD) can be regarded as a challenging semi-supervised node binary classification task. In recent years, Graph Neural Networks (GNN) have been widely applied to GFD, characterizing the anomalous possibility of a node by aggregating neighbor information. However, fraud graphs are inherently heterophilic, thus most of GNNs perform poorly due to their assumption of homophi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.06441v3-abstract-full').style.display = 'inline'; document.getElementById('2312.06441v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.06441v3-abstract-full" style="display: none;"> Graph-based fraud detection (GFD) can be regarded as a challenging semi-supervised node binary classification task. In recent years, Graph Neural Networks (GNN) have been widely applied to GFD, characterizing the anomalous possibility of a node by aggregating neighbor information. However, fraud graphs are inherently heterophilic, thus most of GNNs perform poorly due to their assumption of homophily. In addition, due to the existence of heterophily and class imbalance problem, the existing models do not fully utilize the precious node label information. To address the above issues, this paper proposes a semi-supervised GNN-based fraud detector SEC-GFD. This detector includes a hybrid filtering module and a local environmental constraint module, the two modules are utilized to solve heterophily and label utilization problem respectively. The first module starts from the perspective of the spectral domain, and solves the heterophily problem to a certain extent. Specifically, it divides the spectrum into various mixed-frequency bands based on the correlation between spectrum energy distribution and heterophily. Then in order to make full use of the node label information, a local environmental constraint module is adaptively designed. The comprehensive experimental results on four real-world fraud detection datasets denote that SEC-GFD outperforms other competitive graph-based fraud detectors. We release our code at https://github.com/Sunxkissed/SEC-GFD. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.06441v3-abstract-full').style.display = 'none'; document.getElementById('2312.06441v3-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 11 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.01601">arXiv:2312.01601</a> <span> [<a href="https://arxiv.org/pdf/2312.01601">pdf</a>, <a href="https://arxiv.org/format/2312.01601">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"> Local-Global History-aware Contrastive Learning for Temporal Knowledge Graph Reasoning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+W">Wei Chen</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Huaiyu Wan</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yuting Wu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+S">Shuyuan Zhao</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+J">Jiayaqi Cheng</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yuxin Li</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Youfang Lin</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2312.01601v1-abstract-short" style="display: inline;"> Temporal knowledge graphs (TKGs) have been identified as a promising approach to represent the dynamics of facts along the timeline. The extrapolation of TKG is to predict unknowable facts happening in the future, holding significant practical value across diverse fields. Most extrapolation studies in TKGs focus on modeling global historical fact repeating and cyclic patterns, as well as local his… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.01601v1-abstract-full').style.display = 'inline'; document.getElementById('2312.01601v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.01601v1-abstract-full" style="display: none;"> Temporal knowledge graphs (TKGs) have been identified as a promising approach to represent the dynamics of facts along the timeline. The extrapolation of TKG is to predict unknowable facts happening in the future, holding significant practical value across diverse fields. Most extrapolation studies in TKGs focus on modeling global historical fact repeating and cyclic patterns, as well as local historical adjacent fact evolution patterns, showing promising performance in predicting future unknown facts. Yet, existing methods still face two major challenges: (1) They usually neglect the importance of historical information in KG snapshots related to the queries when encoding the local and global historical information; (2) They exhibit weak anti-noise capabilities, which hinders their performance when the inputs are contaminated with noise.To this end, we propose a novel \blue{Lo}cal-\blue{g}lobal history-aware \blue{C}ontrastive \blue{L}earning model (\blue{LogCL}) for TKG reasoning, which adopts contrastive learning to better guide the fusion of local and global historical information and enhance the ability to resist interference. Specifically, for the first challenge, LogCL proposes an entity-aware attention mechanism applied to the local and global historical facts encoder, which captures the key historical information related to queries. For the latter issue, LogCL designs four historical query contrast patterns, effectively improving the robustness of the model. The experimental results on four benchmark datasets demonstrate that LogCL delivers better and more robust performance than the state-of-the-art baselines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.01601v1-abstract-full').style.display = 'none'; document.getElementById('2312.01601v1-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 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">14 pages, Accept ICDE2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2311.08705">arXiv:2311.08705</a> <span> [<a href="https://arxiv.org/pdf/2311.08705">pdf</a>, <a href="https://arxiv.org/format/2311.08705">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"> Evaluating Robustness of Dialogue Summarization Models in the Presence of Naturally Occurring Variations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gupta%2C+A">Ankita Gupta</a>, <a href="/search/cs?searchtype=author&query=Gunasekara%2C+C">Chulaka Gunasekara</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Hui Wan</a>, <a href="/search/cs?searchtype=author&query=Ganhotra%2C+J">Jatin Ganhotra</a>, <a href="/search/cs?searchtype=author&query=Joshi%2C+S">Sachindra Joshi</a>, <a href="/search/cs?searchtype=author&query=Danilevsky%2C+M">Marina Danilevsky</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2311.08705v1-abstract-short" style="display: inline;"> Dialogue summarization task involves summarizing long conversations while preserving the most salient information. Real-life dialogues often involve naturally occurring variations (e.g., repetitions, hesitations) and existing dialogue summarization models suffer from performance drop on such conversations. In this study, we systematically investigate the impact of such variations on state-of-the-a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.08705v1-abstract-full').style.display = 'inline'; document.getElementById('2311.08705v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2311.08705v1-abstract-full" style="display: none;"> Dialogue summarization task involves summarizing long conversations while preserving the most salient information. Real-life dialogues often involve naturally occurring variations (e.g., repetitions, hesitations) and existing dialogue summarization models suffer from performance drop on such conversations. In this study, we systematically investigate the impact of such variations on state-of-the-art dialogue summarization models using publicly available datasets. To simulate real-life variations, we introduce two types of perturbations: utterance-level perturbations that modify individual utterances with errors and language variations, and dialogue-level perturbations that add non-informative exchanges (e.g., repetitions, greetings). We conduct our analysis along three dimensions of robustness: consistency, saliency, and faithfulness, which capture different aspects of the summarization model's performance. We find that both fine-tuned and instruction-tuned models are affected by input variations, with the latter being more susceptible, particularly to dialogue-level perturbations. We also validate our findings via human evaluation. Finally, we investigate if the robustness of fine-tuned models can be improved by training them with a fraction of perturbed data and observe that this approach is insufficient to address robustness challenges with current models and thus warrants a more thorough investigation to identify better solutions. Overall, our work highlights robustness challenges in dialogue summarization and provides insights for future research. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.08705v1-abstract-full').style.display = 'none'; document.getElementById('2311.08705v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2311.01759">arXiv:2311.01759</a> <span> [<a href="https://arxiv.org/pdf/2311.01759">pdf</a>, <a href="https://arxiv.org/format/2311.01759">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="Hardware Architecture">cs.AR</span> </div> </div> <p class="title is-5 mathjax"> TinyFormer: Efficient Transformer Design and Deployment on Tiny Devices </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+J">Jianlei Yang</a>, <a href="/search/cs?searchtype=author&query=Liao%2C+J">Jiacheng Liao</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+F">Fanding Lei</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+M">Meichen Liu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+J">Junyi Chen</a>, <a href="/search/cs?searchtype=author&query=Long%2C+L">Lingkun Long</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Han Wan</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+B">Bei Yu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+W">Weisheng 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="2311.01759v1-abstract-short" style="display: inline;"> Developing deep learning models on tiny devices (e.g. Microcontroller units, MCUs) has attracted much attention in various embedded IoT applications. However, it is challenging to efficiently design and deploy recent advanced models (e.g. transformers) on tiny devices due to their severe hardware resource constraints. In this work, we propose TinyFormer, a framework specifically designed to develo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.01759v1-abstract-full').style.display = 'inline'; document.getElementById('2311.01759v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2311.01759v1-abstract-full" style="display: none;"> Developing deep learning models on tiny devices (e.g. Microcontroller units, MCUs) has attracted much attention in various embedded IoT applications. However, it is challenging to efficiently design and deploy recent advanced models (e.g. transformers) on tiny devices due to their severe hardware resource constraints. In this work, we propose TinyFormer, a framework specifically designed to develop and deploy resource-efficient transformers on MCUs. TinyFormer mainly consists of SuperNAS, SparseNAS and SparseEngine. Separately, SuperNAS aims to search for an appropriate supernet from a vast search space. SparseNAS evaluates the best sparse single-path model including transformer architecture from the identified supernet. Finally, SparseEngine efficiently deploys the searched sparse models onto MCUs. To the best of our knowledge, SparseEngine is the first deployment framework capable of performing inference of sparse models with transformer on MCUs. Evaluation results on the CIFAR-10 dataset demonstrate that TinyFormer can develop efficient transformers with an accuracy of $96.1\%$ while adhering to hardware constraints of $1$MB storage and $320$KB memory. Additionally, TinyFormer achieves significant speedups in sparse inference, up to $12.2\times$, when compared to the CMSIS-NN library. TinyFormer is believed to bring powerful transformers into TinyML scenarios and greatly expand the scope of deep learning applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.01759v1-abstract-full').style.display = 'none'; document.getElementById('2311.01759v1-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 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">This work has been submitted to the IEEE for possible publication</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.13411">arXiv:2310.13411</a> <span> [<a href="https://arxiv.org/pdf/2310.13411">pdf</a>, <a href="https://arxiv.org/format/2310.13411">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 Enhancing Relational Rules for Knowledge Graph Link Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+S">Shuhan Wu</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Huaiyu Wan</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+W">Wei Chen</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yuting Wu</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+J">Junfeng Shen</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Youfang Lin</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2310.13411v1-abstract-short" style="display: inline;"> Graph neural networks (GNNs) have shown promising performance for knowledge graph reasoning. A recent variant of GNN called progressive relational graph neural network (PRGNN), utilizes relational rules to infer missing knowledge in relational digraphs and achieves notable results. However, during reasoning with PRGNN, two important properties are often overlooked: (1) the sequentiality of relatio… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.13411v1-abstract-full').style.display = 'inline'; document.getElementById('2310.13411v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.13411v1-abstract-full" style="display: none;"> Graph neural networks (GNNs) have shown promising performance for knowledge graph reasoning. A recent variant of GNN called progressive relational graph neural network (PRGNN), utilizes relational rules to infer missing knowledge in relational digraphs and achieves notable results. However, during reasoning with PRGNN, two important properties are often overlooked: (1) the sequentiality of relation composition, where the order of combining different relations affects the semantics of the relational rules, and (2) the lagged entity information propagation, where the transmission speed of required information lags behind the appearance speed of new entities. Ignoring these properties leads to incorrect relational rule learning and decreased reasoning accuracy. To address these issues, we propose a novel knowledge graph reasoning approach, the Relational rUle eNhanced Graph Neural Network (RUN-GNN). Specifically, RUN-GNN employs a query related fusion gate unit to model the sequentiality of relation composition and utilizes a buffering update mechanism to alleviate the negative effect of lagged entity information propagation, resulting in higher-quality relational rule learning. Experimental results on multiple datasets demonstrate the superiority of RUN-GNN is superior on both transductive and inductive link prediction tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.13411v1-abstract-full').style.display = 'none'; document.getElementById('2310.13411v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at Findings of EMNLP2023</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2309.11902">arXiv:2309.11902</a> <span> [<a href="https://arxiv.org/pdf/2309.11902">pdf</a>, <a href="https://arxiv.org/format/2309.11902">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Hardware Architecture">cs.AR</span> </div> </div> <p class="title is-5 mathjax"> A Switch Architecture for Time-Triggered Transmission with Best-Effort Delivery </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+Z">Zonghui Li</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+W">Wenlin Zhu</a>, <a href="/search/cs?searchtype=author&query=Shin%2C+K+G">Kang G. Shin</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Hai Wan</a>, <a href="/search/cs?searchtype=author&query=Song%2C+X">Xiaoyu Song</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+D">Dong Yang</a>, <a href="/search/cs?searchtype=author&query=Ai%2C+B">Bo Ai</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2309.11902v1-abstract-short" style="display: inline;"> In Time-Triggered (TT) or time-sensitive networks, the transmission of a TT frame is required to be scheduled at a precise time instant for industrial distributed real-time control systems. Other (or {\em best-effort} (BE)) frames are forwarded in a BE manner. Under this scheduling strategy, the transmission of a TT frame must wait until its scheduled instant even if it could have been transmitted… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.11902v1-abstract-full').style.display = 'inline'; document.getElementById('2309.11902v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.11902v1-abstract-full" style="display: none;"> In Time-Triggered (TT) or time-sensitive networks, the transmission of a TT frame is required to be scheduled at a precise time instant for industrial distributed real-time control systems. Other (or {\em best-effort} (BE)) frames are forwarded in a BE manner. Under this scheduling strategy, the transmission of a TT frame must wait until its scheduled instant even if it could have been transmitted sooner. On the other hand, BE frames are transmitted whenever possible but may miss deadlines or may even be dropped due to congestion. As a result, TT transmission and BE delivery are incompatible with each other. To remedy this incompatibility, we propose a synergistic switch architecture (SWA) for TT transmission with BE delivery to dynamically improve the end-to-end (e2e) latency of TT frames by opportunistically exploiting BE delivery. Given a TT frame, the SWA generates and transmits a cloned copy with BE delivery. The first frame arriving at the receiver device is delivered with a configured jitter and the other copy ignored. So, the SWA achieves shorter latency and controllable jitter, the best of both worlds. We have implemented SWA using FPGAs in an industry-strength TT switches and used four test scenarios to demonstrate SWA's improvements of e2e latency and controllable jitter over the state-of-the-art TT transmission scheme. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.11902v1-abstract-full').style.display = 'none'; document.getElementById('2309.11902v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">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/2309.04891">arXiv:2309.04891</a> <span> [<a href="https://arxiv.org/pdf/2309.04891">pdf</a>, <a href="https://arxiv.org/format/2309.04891">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> How to Evaluate Semantic Communications for Images with ViTScore Metric? </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhu%2C+T">Tingting Zhu</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+B">Bo Peng</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+J">Jifan Liang</a>, <a href="/search/cs?searchtype=author&query=Han%2C+T">Tingchen Han</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Hai Wan</a>, <a href="/search/cs?searchtype=author&query=Fu%2C+J">Jingqiao Fu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+J">Junjie Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2309.04891v2-abstract-short" style="display: inline;"> Semantic communications (SC) have been expected to be a new paradigm shifting to catalyze the next generation communication, whose main concerns shift from accurate bit transmission to effective semantic information exchange in communications. However, the previous and widely-used metrics for images are not applicable to evaluate the image semantic similarity in SC. Classical metrics to measure th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.04891v2-abstract-full').style.display = 'inline'; document.getElementById('2309.04891v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.04891v2-abstract-full" style="display: none;"> Semantic communications (SC) have been expected to be a new paradigm shifting to catalyze the next generation communication, whose main concerns shift from accurate bit transmission to effective semantic information exchange in communications. However, the previous and widely-used metrics for images are not applicable to evaluate the image semantic similarity in SC. Classical metrics to measure the similarity between two images usually rely on the pixel level or the structural level, such as the PSNR and the MS-SSIM. Straightforwardly using some tailored metrics based on deep-learning methods in CV community, such as the LPIPS, is infeasible for SC. To tackle this, inspired by BERTScore in NLP community, we propose a novel metric for evaluating image semantic similarity, named Vision Transformer Score (ViTScore). We prove theoretically that ViTScore has 3 important properties, including symmetry, boundedness, and normalization, which make ViTScore convenient and intuitive for image measurement. To evaluate the performance of ViTScore, we compare ViTScore with 3 typical metrics (PSNR, MS-SSIM, and LPIPS) through 4 classes of experiments: (i) correlation with BERTScore through evaluation of image caption downstream CV task, (ii) evaluation in classical image communications, (iii) evaluation in image semantic communication systems, and (iv) evaluation in image semantic communication systems with semantic attack. Experimental results demonstrate that ViTScore is robust and efficient in evaluating the semantic similarity of images. Particularly, ViTScore outperforms the other 3 typical metrics in evaluating the image semantic changes by semantic attack, such as image inverse with Generative Adversarial Networks (GANs). This indicates that ViTScore is an effective performance metric when deployed in SC scenarios. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.04891v2-abstract-full').style.display = 'none'; document.getElementById('2309.04891v2-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 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2309.01194">arXiv:2309.01194</a> <span> [<a href="https://arxiv.org/pdf/2309.01194">pdf</a>, <a href="https://arxiv.org/format/2309.01194">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"> A Survey on Service Route and Time Prediction in Instant Delivery: Taxonomy, Progress, and Prospects </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wen%2C+H">Haomin Wen</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Youfang Lin</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+L">Lixia Wu</a>, <a href="/search/cs?searchtype=author&query=Mao%2C+X">Xiaowei Mao</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+T">Tianyue Cai</a>, <a href="/search/cs?searchtype=author&query=Hou%2C+Y">Yunfeng Hou</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+S">Shengnan Guo</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+Y">Yuxuan Liang</a>, <a href="/search/cs?searchtype=author&query=Jin%2C+G">Guangyin Jin</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Y">Yiji Zhao</a>, <a href="/search/cs?searchtype=author&query=Zimmermann%2C+R">Roger Zimmermann</a>, <a href="/search/cs?searchtype=author&query=Ye%2C+J">Jieping Ye</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Huaiyu Wan</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2309.01194v1-abstract-short" style="display: inline;"> Instant delivery services, such as food delivery and package delivery, have achieved explosive growth in recent years by providing customers with daily-life convenience. An emerging research area within these services is service Route\&Time Prediction (RTP), which aims to estimate the future service route as well as the arrival time of a given worker. As one of the most crucial tasks in those serv… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.01194v1-abstract-full').style.display = 'inline'; document.getElementById('2309.01194v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.01194v1-abstract-full" style="display: none;"> Instant delivery services, such as food delivery and package delivery, have achieved explosive growth in recent years by providing customers with daily-life convenience. An emerging research area within these services is service Route\&Time Prediction (RTP), which aims to estimate the future service route as well as the arrival time of a given worker. As one of the most crucial tasks in those service platforms, RTP stands central to enhancing user satisfaction and trimming operational expenditures on these platforms. Despite a plethora of algorithms developed to date, there is no systematic, comprehensive survey to guide researchers in this domain. To fill this gap, our work presents the first comprehensive survey that methodically categorizes recent advances in service route and time prediction. We start by defining the RTP challenge and then delve into the metrics that are often employed. Following that, we scrutinize the existing RTP methodologies, presenting a novel taxonomy of them. We categorize these methods based on three criteria: (i) type of task, subdivided into only-route prediction, only-time prediction, and joint route\&time prediction; (ii) model architecture, which encompasses sequence-based and graph-based models; and (iii) learning paradigm, including Supervised Learning (SL) and Deep Reinforcement Learning (DRL). Conclusively, we highlight the limitations of current research and suggest prospective avenues. We believe that the taxonomy, progress, and prospects introduced in this paper can significantly promote the development of this field. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.01194v1-abstract-full').style.display = 'none'; document.getElementById('2309.01194v1-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 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.13760">arXiv:2308.13760</a> <span> [<a href="https://arxiv.org/pdf/2308.13760">pdf</a>, <a href="https://arxiv.org/format/2308.13760">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="Computation and Language">cs.CL</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"> How Can Context Help? Exploring Joint Retrieval of Passage and Personalized Context </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wan%2C+H">Hui Wan</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Hongkang Li</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+S">Songtao Lu</a>, <a href="/search/cs?searchtype=author&query=Cui%2C+X">Xiaodong Cui</a>, <a href="/search/cs?searchtype=author&query=Danilevsky%2C+M">Marina Danilevsky</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2308.13760v1-abstract-short" style="display: inline;"> The integration of external personalized context information into document-grounded conversational systems has significant potential business value, but has not been well-studied. Motivated by the concept of personalized context-aware document-grounded conversational systems, we introduce the task of context-aware passage retrieval. We also construct a dataset specifically curated for this purpose… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.13760v1-abstract-full').style.display = 'inline'; document.getElementById('2308.13760v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.13760v1-abstract-full" style="display: none;"> The integration of external personalized context information into document-grounded conversational systems has significant potential business value, but has not been well-studied. Motivated by the concept of personalized context-aware document-grounded conversational systems, we introduce the task of context-aware passage retrieval. We also construct a dataset specifically curated for this purpose. We describe multiple baseline systems to address this task, and propose a novel approach, Personalized Context-Aware Search (PCAS), that effectively harnesses contextual information during passage retrieval. Experimental evaluations conducted on multiple popular dense retrieval systems demonstrate that our proposed approach not only outperforms the baselines in retrieving the most relevant passage but also excels at identifying the pertinent context among all the available contexts. We envision that our contributions will serve as a catalyst for inspiring future research endeavors in this promising direction. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.13760v1-abstract-full').style.display = 'none'; document.getElementById('2308.13760v1-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, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.16246">arXiv:2307.16246</a> <span> [<a href="https://arxiv.org/pdf/2307.16246">pdf</a>, <a href="https://arxiv.org/format/2307.16246">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"> DRL4Route: A Deep Reinforcement Learning Framework for Pick-up and Delivery Route Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mao%2C+X">Xiaowei Mao</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+H">Haomin Wen</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+H">Hengrui Zhang</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+H">Huaiyu Wan</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+L">Lixia Wu</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+J">Jianbin Zheng</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+H">Haoyuan Hu</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Youfang Lin</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2307.16246v1-abstract-short" style="display: inline;"> Pick-up and Delivery Route Prediction (PDRP), which aims to estimate the future service route of a worker given his current task pool, has received rising attention in recent years. Deep neural networks based on supervised learning have emerged as the dominant model for the task because of their powerful ability to capture workers' behavior patterns from massive historical data. Though promising,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.16246v1-abstract-full').style.display = 'inline'; document.getElementById('2307.16246v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.16246v1-abstract-full" style="display: none;"> Pick-up and Delivery Route Prediction (PDRP), which aims to estimate the future service route of a worker given his current task pool, has received rising attention in recent years. Deep neural networks based on supervised learning have emerged as the dominant model for the task because of their powerful ability to capture workers' behavior patterns from massive historical data. Though promising, they fail to introduce the non-differentiable test criteria into the training process, leading to a mismatch in training and test criteria. Which considerably trims down their performance when applied in practical systems. To tackle the above issue, we present the first attempt to generalize Reinforcement Learning (RL) to the route prediction task, leading to a novel RL-based framework called DRL4Route. It combines the behavior-learning abilities of previous deep learning models with the non-differentiable objective optimization ability of reinforcement learning. DRL4Route can serve as a plug-and-play component to boost the existing deep learning models. Based on the framework, we further implement a model named DRL4Route-GAE for PDRP in logistic service. It follows the actor-critic architecture which is equipped with a Generalized Advantage Estimator that can balance the bias and variance of the policy gradient estimates, thus achieving a more optimal policy. Extensive offline experiments and the online deployment show that DRL4Route-GAE improves Location Square Deviation (LSD) by 0.9%-2.7%, and Accuracy@3 (ACC@3) by 2.4%-3.2% over existing methods on the real-world dataset. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.16246v1-abstract-full').style.display = 'none'; document.getElementById('2307.16246v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by KDD23</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=Wan%2C+H&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Wan%2C+H&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Wan%2C+H&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Wan%2C+H&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> </ul> </nav> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository