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 1–48 of 48 results for author: <span class="mathjax">Qu, M</span> </h1> </div> <div class="level-right is-hidden-mobile">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> <div class="content"> <form method="GET" action="/search/cs" aria-role="search"> Searching in archive <strong>cs</strong>. <a href="/search/?searchtype=author&query=Qu%2C+M">Search in all archives.</a> <div class="field has-addons-tablet"> <div class="control is-expanded"> <label for="query" class="hidden-label">Search term or terms</label> <input class="input is-medium" id="query" name="query" placeholder="Search term..." type="text" value="Qu, M"> </div> <div class="select control is-medium"> <label class="is-hidden" for="searchtype">Field</label> <select class="is-medium" id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> </div> <div class="control"> <button class="button is-link is-medium">Search</button> </div> </div> <div class="field"> <div class="control is-size-7"> <label class="radio"> <input checked id="abstracts-0" name="abstracts" type="radio" value="show"> Show abstracts </label> <label class="radio"> <input id="abstracts-1" name="abstracts" type="radio" value="hide"> Hide abstracts </label> </div> </div> <div class="is-clearfix" style="height: 2.5em"> <div class="is-pulled-right"> <a href="/search/advanced?terms-0-term=Qu%2C+M&terms-0-field=author&size=50&order=-announced_date_first">Advanced Search</a> </div> </div> <input type="hidden" name="order" value="-announced_date_first"> <input type="hidden" name="size" value="50"> </form> <div class="level breathe-horizontal"> <div class="level-left"> <form method="GET" action="/search/"> <div style="display: none;"> <select id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> <input id="query" name="query" type="text" value="Qu, M"> <ul id="abstracts"><li><input checked id="abstracts-0" name="abstracts" type="radio" value="show"> <label for="abstracts-0">Show abstracts</label></li><li><input id="abstracts-1" name="abstracts" type="radio" value="hide"> <label for="abstracts-1">Hide abstracts</label></li></ul> </div> <div class="box field is-grouped is-grouped-multiline level-item"> <div class="control"> <span class="select is-small"> <select id="size" name="size"><option value="25">25</option><option selected value="50">50</option><option value="100">100</option><option value="200">200</option></select> </span> <label for="size">results per page</label>. </div> <div class="control"> <label for="order">Sort results by</label> <span class="select is-small"> <select id="order" name="order"><option selected value="-announced_date_first">Announcement date (newest first)</option><option value="announced_date_first">Announcement date (oldest first)</option><option value="-submitted_date">Submission date (newest first)</option><option value="submitted_date">Submission date (oldest first)</option><option value="">Relevance</option></select> </span> </div> <div class="control"> <button class="button is-small is-link">Go</button> </div> </div> </form> </div> </div> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.16210">arXiv:2502.16210</a> <span> [<a href="https://arxiv.org/pdf/2502.16210">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computational Engineering, Finance, and Science">cs.CE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1016/j.compenvurbsys.2025.102267">10.1016/j.compenvurbsys.2025.102267 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Interpreting core forms of urban morphology linked to urban functions with explainable graph neural network </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+D">Dongsheng Chen</a>, <a href="/search/cs?searchtype=author&query=Feng%2C+Y">Yu Feng</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xun Li</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+M">Mingya Qu</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+P">Peng Luo</a>, <a href="/search/cs?searchtype=author&query=Meng%2C+L">Liqiu Meng</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2502.16210v1-abstract-short" style="display: inline;"> Understanding the high-order relationship between urban form and function is essential for modeling the underlying mechanisms of sustainable urban systems. Nevertheless, it is challenging to establish an accurate data representation for complex urban forms that are readily explicable in human terms. This study proposed the concept of core urban morphology representation and developed an explainabl… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.16210v1-abstract-full').style.display = 'inline'; document.getElementById('2502.16210v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.16210v1-abstract-full" style="display: none;"> Understanding the high-order relationship between urban form and function is essential for modeling the underlying mechanisms of sustainable urban systems. Nevertheless, it is challenging to establish an accurate data representation for complex urban forms that are readily explicable in human terms. This study proposed the concept of core urban morphology representation and developed an explainable deep learning framework for explicably symbolizing complex urban forms into the novel representation, which we call CoMo. By interpretating the well-trained deep learning model with a stable weighted F1-score of 89.14%, CoMo presents a promising approach for revealing links between urban function and urban form in terms of core urban morphology representation. Using Boston as a study area, we analyzed the core urban forms at the individual-building, block, and neighborhood level that are important to corresponding urban functions. The residential core forms follow a gradual morphological pattern along the urban spine, which is consistent with a center-urban-suburban transition. Furthermore, we prove that urban morphology directly affects land use efficiency, which has a significantly strong correlation with the location (R2=0.721, p<0.001). Overall, CoMo can explicably symbolize urban forms, provide evidence for the classic urban location theory, and offer mechanistic insights for digital twins. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.16210v1-abstract-full').style.display = 'none'; document.getElementById('2502.16210v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.04072">arXiv:2412.04072</a> <span> [<a href="https://arxiv.org/pdf/2412.04072">pdf</a>, <a href="https://arxiv.org/format/2412.04072">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"> Boundary-Guided Learning for Gene Expression Prediction in Spatial Transcriptomics </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Qu%2C+M">Mingcheng Qu</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yuncong Wu</a>, <a href="/search/cs?searchtype=author&query=Di%2C+D">Donglin Di</a>, <a href="/search/cs?searchtype=author&query=Su%2C+A">Anyang Su</a>, <a href="/search/cs?searchtype=author&query=Su%2C+T">Tonghua Su</a>, <a href="/search/cs?searchtype=author&query=Song%2C+Y">Yang Song</a>, <a href="/search/cs?searchtype=author&query=Fan%2C+L">Lei Fan</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="2412.04072v2-abstract-short" style="display: inline;"> Spatial transcriptomics (ST) has emerged as an advanced technology that provides spatial context to gene expression. Recently, deep learning-based methods have shown the capability to predict gene expression from WSI data using ST data. Existing approaches typically extract features from images and the neighboring regions using pretrained models, and then develop methods to fuse this information t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.04072v2-abstract-full').style.display = 'inline'; document.getElementById('2412.04072v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.04072v2-abstract-full" style="display: none;"> Spatial transcriptomics (ST) has emerged as an advanced technology that provides spatial context to gene expression. Recently, deep learning-based methods have shown the capability to predict gene expression from WSI data using ST data. Existing approaches typically extract features from images and the neighboring regions using pretrained models, and then develop methods to fuse this information to generate the final output. However, these methods often fail to account for the cellular structure similarity, cellular density and the interactions within the microenvironment. In this paper, we propose a framework named BG-TRIPLEX, which leverages boundary information extracted from pathological images as guiding features to enhance gene expression prediction from WSIs. Specifically, our model consists of three branches: the spot, in-context and global branches. In the spot and in-context branches, boundary information, including edge and nuclei characteristics, is extracted using pretrained models. These boundary features guide the learning of cellular morphology and the characteristics of microenvironment through Multi-Head Cross-Attention. Finally, these features are integrated with global features to predict the final output. Extensive experiments were conducted on three public ST datasets. The results demonstrate that our BG-TRIPLEX consistently outperforms existing methods in terms of Pearson Correlation Coefficient (PCC). This method highlights the crucial role of boundary features in understanding the complex interactions between WSI and gene expression, offering a promising direction for future research. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.04072v2-abstract-full').style.display = 'none'; document.getElementById('2412.04072v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 pages, 5 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.00153">arXiv:2412.00153</a> <span> [<a href="https://arxiv.org/pdf/2412.00153">pdf</a>, <a href="https://arxiv.org/format/2412.00153">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"> ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Han%2C+K">Kunyang Han</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+Y">Yibo Hu</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+M">Mengxue Qu</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+H">Hailin Shi</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Y">Yao Zhao</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+Y">Yunchao Wei</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="2412.00153v2-abstract-short" style="display: inline;"> Advances in CLIP and large multimodal models (LMMs) have enabled open-vocabulary and free-text segmentation, yet existing models still require predefined category prompts, limiting free-form category self-generation. Most segmentation LMMs also remain confined to sparse predictions, restricting their applicability in open-set environments. In contrast, we propose ROSE, a Revolutionary Open-set den… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.00153v2-abstract-full').style.display = 'inline'; document.getElementById('2412.00153v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.00153v2-abstract-full" style="display: none;"> Advances in CLIP and large multimodal models (LMMs) have enabled open-vocabulary and free-text segmentation, yet existing models still require predefined category prompts, limiting free-form category self-generation. Most segmentation LMMs also remain confined to sparse predictions, restricting their applicability in open-set environments. In contrast, we propose ROSE, a Revolutionary Open-set dense SEgmentation LMM, which enables dense mask prediction and open-category generation through patch-wise perception. Our method treats each image patch as an independent region of interest candidate, enabling the model to predict both dense and sparse masks simultaneously. Additionally, a newly designed instruction-response paradigm takes full advantage of the generation and generalization capabilities of LMMs, achieving category prediction independent of closed-set constraints or predefined categories. To further enhance mask detail and category precision, we introduce a conversation-based refinement paradigm, integrating the prediction result from previous step with textual prompt for revision. Extensive experiments demonstrate that ROSE achieves competitive performance across various segmentation tasks in a unified framework. Code will be released. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.00153v2-abstract-full').style.display = 'none'; document.getElementById('2412.00153v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 29 November, 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/2410.12813">arXiv:2410.12813</a> <span> [<a href="https://arxiv.org/pdf/2410.12813">pdf</a>, <a href="https://arxiv.org/format/2410.12813">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> ChatVTG: Video Temporal Grounding via Chat with Video Dialogue Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Qu%2C+M">Mengxue Qu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xiaodong Chen</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+W">Wu Liu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+A">Alicia Li</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Y">Yao 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="2410.12813v1-abstract-short" style="display: inline;"> Video Temporal Grounding (VTG) aims to ground specific segments within an untrimmed video corresponding to the given natural language query. Existing VTG methods largely depend on supervised learning and extensive annotated data, which is labor-intensive and prone to human biases. To address these challenges, we present ChatVTG, a novel approach that utilizes Video Dialogue Large Language Models (… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.12813v1-abstract-full').style.display = 'inline'; document.getElementById('2410.12813v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.12813v1-abstract-full" style="display: none;"> Video Temporal Grounding (VTG) aims to ground specific segments within an untrimmed video corresponding to the given natural language query. Existing VTG methods largely depend on supervised learning and extensive annotated data, which is labor-intensive and prone to human biases. To address these challenges, we present ChatVTG, a novel approach that utilizes Video Dialogue Large Language Models (LLMs) for zero-shot video temporal grounding. Our ChatVTG leverages Video Dialogue LLMs to generate multi-granularity segment captions and matches these captions with the given query for coarse temporal grounding, circumventing the need for paired annotation data. Furthermore, to obtain more precise temporal grounding results, we employ moment refinement for fine-grained caption proposals. Extensive experiments on three mainstream VTG datasets, including Charades-STA, ActivityNet-Captions, and TACoS, demonstrate the effectiveness of ChatVTG. Our ChatVTG surpasses the performance of current zero-shot methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.12813v1-abstract-full').style.display = 'none'; document.getElementById('2410.12813v1-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">10 pages, 3 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/2410.09954">arXiv:2410.09954</a> <span> [<a href="https://arxiv.org/pdf/2410.09954">pdf</a>, <a href="https://arxiv.org/format/2410.09954">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> EITNet: An IoT-Enhanced Framework for Real-Time Basketball Action Recognition </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jingyu Liu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xinyu Liu</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+M">Mingzhe Qu</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+T">Tianyi Lyu</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="2410.09954v1-abstract-short" style="display: inline;"> Integrating IoT technology into basketball action recognition enhances sports analytics, providing crucial insights into player performance and game strategy. However, existing methods often fall short in terms of accuracy and efficiency, particularly in complex, real-time environments where player movements are frequently occluded or involve intricate interactions. To overcome these challenges, w… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.09954v1-abstract-full').style.display = 'inline'; document.getElementById('2410.09954v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.09954v1-abstract-full" style="display: none;"> Integrating IoT technology into basketball action recognition enhances sports analytics, providing crucial insights into player performance and game strategy. However, existing methods often fall short in terms of accuracy and efficiency, particularly in complex, real-time environments where player movements are frequently occluded or involve intricate interactions. To overcome these challenges, we propose the EITNet model, a deep learning framework that combines EfficientDet for object detection, I3D for spatiotemporal feature extraction, and TimeSformer for temporal analysis, all integrated with IoT technology for seamless real-time data collection and processing. Our contributions include developing a robust architecture that improves recognition accuracy to 92\%, surpassing the baseline EfficientDet model's 87\%, and reducing loss to below 5.0 compared to EfficientDet's 9.0 over 50 epochs. Furthermore, the integration of IoT technology enhances real-time data processing, providing adaptive insights into player performance and strategy. The paper details the design and implementation of EITNet, experimental validation, and a comprehensive evaluation against existing models. The results demonstrate EITNet's potential to significantly advance automated sports analysis and optimize data utilization for player performance and strategy improvement. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.09954v1-abstract-full').style.display = 'none'; document.getElementById('2410.09954v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 October, 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">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/2409.04768">arXiv:2409.04768</a> <span> [<a href="https://arxiv.org/pdf/2409.04768">pdf</a>, <a href="https://arxiv.org/format/2409.04768">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Medical Image Segmentation via Single-Source Domain Generalization with Random Amplitude Spectrum Synthesis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Qiao%2C+Q">Qiang Qiao</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+W">Wenyu Wang</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meixia Qu</a>, <a href="/search/cs?searchtype=author&query=Su%2C+K">Kun Su</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+B">Bin Jiang</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+Q">Qiang Guo</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="2409.04768v1-abstract-short" style="display: inline;"> The field of medical image segmentation is challenged by domain generalization (DG) due to domain shifts in clinical datasets. The DG challenge is exacerbated by the scarcity of medical data and privacy concerns. Traditional single-source domain generalization (SSDG) methods primarily rely on stacking data augmentation techniques to minimize domain discrepancies. In this paper, we propose Random A… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.04768v1-abstract-full').style.display = 'inline'; document.getElementById('2409.04768v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.04768v1-abstract-full" style="display: none;"> The field of medical image segmentation is challenged by domain generalization (DG) due to domain shifts in clinical datasets. The DG challenge is exacerbated by the scarcity of medical data and privacy concerns. Traditional single-source domain generalization (SSDG) methods primarily rely on stacking data augmentation techniques to minimize domain discrepancies. In this paper, we propose Random Amplitude Spectrum Synthesis (RASS) as a training augmentation for medical images. RASS enhances model generalization by simulating distribution changes from a frequency perspective. This strategy introduces variability by applying amplitude-dependent perturbations to ensure broad coverage of potential domain variations. Furthermore, we propose random mask shuffle and reconstruction components, which can enhance the ability of the backbone to process structural information and increase resilience intra- and cross-domain changes. The proposed Random Amplitude Spectrum Synthesis for Single-Source Domain Generalization (RAS^4DG) is validated on 3D fetal brain images and 2D fundus photography, and achieves an improved DG segmentation performance compared to other SSDG models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.04768v1-abstract-full').style.display = 'none'; document.getElementById('2409.04768v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">11 pages, 4 figures, Medical Image Computing and Computer Assisted Intervention 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.03251">arXiv:2407.03251</a> <span> [<a href="https://arxiv.org/pdf/2407.03251">pdf</a>, <a href="https://arxiv.org/format/2407.03251">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> ACTRESS: Active Retraining for Semi-supervised Visual Grounding </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kang%2C+W">Weitai Kang</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+M">Mengxue Qu</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+Y">Yunchao Wei</a>, <a href="/search/cs?searchtype=author&query=Yan%2C+Y">Yan Yan</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.03251v2-abstract-short" style="display: inline;"> Semi-Supervised Visual Grounding (SSVG) is a new challenge for its sparse labeled data with the need for multimodel understanding. A previous study, RefTeacher, makes the first attempt to tackle this task by adopting the teacher-student framework to provide pseudo confidence supervision and attention-based supervision. However, this approach is incompatible with current state-of-the-art visual gro… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.03251v2-abstract-full').style.display = 'inline'; document.getElementById('2407.03251v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.03251v2-abstract-full" style="display: none;"> Semi-Supervised Visual Grounding (SSVG) is a new challenge for its sparse labeled data with the need for multimodel understanding. A previous study, RefTeacher, makes the first attempt to tackle this task by adopting the teacher-student framework to provide pseudo confidence supervision and attention-based supervision. However, this approach is incompatible with current state-of-the-art visual grounding models, which follow the Transformer-based pipeline. These pipelines directly regress results without region proposals or foreground binary classification, rendering them unsuitable for fitting in RefTeacher due to the absence of confidence scores. Furthermore, the geometric difference in teacher and student inputs, stemming from different data augmentations, induces natural misalignment in attention-based constraints. To establish a compatible SSVG framework, our paper proposes the ACTive REtraining approach for Semi-Supervised Visual Grounding, abbreviated as ACTRESS. Initially, the model is enhanced by incorporating an additional quantized detection head to expose its detection confidence. Building upon this, ACTRESS consists of an active sampling strategy and a selective retraining strategy. The active sampling strategy iteratively selects high-quality pseudo labels by evaluating three crucial aspects: Faithfulness, Robustness, and Confidence, optimizing the utilization of unlabeled data. The selective retraining strategy retrains the model with periodic re-initialization of specific parameters, facilitating the model's escape from local minima. Extensive experiments demonstrates our superior performance on widely-used benchmark datasets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.03251v2-abstract-full').style.display = 'none'; document.getElementById('2407.03251v2-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 3 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/2405.18295">arXiv:2405.18295</a> <span> [<a href="https://arxiv.org/pdf/2405.18295">pdf</a>, <a href="https://arxiv.org/format/2405.18295">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Intent3D: 3D Object Detection in RGB-D Scans Based on Human Intention </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kang%2C+W">Weitai Kang</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+M">Mengxue Qu</a>, <a href="/search/cs?searchtype=author&query=Kini%2C+J">Jyoti Kini</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+Y">Yunchao Wei</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+M">Mubarak Shah</a>, <a href="/search/cs?searchtype=author&query=Yan%2C+Y">Yan Yan</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2405.18295v3-abstract-short" style="display: inline;"> In real-life scenarios, humans seek out objects in the 3D world to fulfill their daily needs or intentions. This inspires us to introduce 3D intention grounding, a new task in 3D object detection employing RGB-D, based on human intention, such as "I want something to support my back". Closely related, 3D visual grounding focuses on understanding human reference. To achieve detection based on human… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.18295v3-abstract-full').style.display = 'inline'; document.getElementById('2405.18295v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.18295v3-abstract-full" style="display: none;"> In real-life scenarios, humans seek out objects in the 3D world to fulfill their daily needs or intentions. This inspires us to introduce 3D intention grounding, a new task in 3D object detection employing RGB-D, based on human intention, such as "I want something to support my back". Closely related, 3D visual grounding focuses on understanding human reference. To achieve detection based on human intention, it relies on humans to observe the scene, reason out the target that aligns with their intention ("pillow" in this case), and finally provide a reference to the AI system, such as "A pillow on the couch". Instead, 3D intention grounding challenges AI agents to automatically observe, reason and detect the desired target solely based on human intention. To tackle this challenge, we introduce the new Intent3D dataset, consisting of 44,990 intention texts associated with 209 fine-grained classes from 1,042 scenes of the ScanNet dataset. We also establish several baselines based on different language-based 3D object detection models on our benchmark. Finally, we propose IntentNet, our unique approach, designed to tackle this intention-based detection problem. It focuses on three key aspects: intention understanding, reasoning to identify object candidates, and cascaded adaptive learning that leverages the intrinsic priority logic of different losses for multiple objective optimization. Project Page: https://weitaikang.github.io/Intent3D-webpage/ <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.18295v3-abstract-full').style.display = 'none'; document.getElementById('2405.18295v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 28 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">ICLR 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.10757">arXiv:2404.10757</a> <span> [<a href="https://arxiv.org/pdf/2404.10757">pdf</a>, <a href="https://arxiv.org/format/2404.10757">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Instrumentation and Methods for Astrophysics">astro-ph.IM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Solar and Stellar Astrophysics">astro-ph.SR</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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Deep Learning and LLM-based Methods Applied to Stellar Lightcurve Classification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yu-Yang Li</a>, <a href="/search/cs?searchtype=author&query=Bai%2C+Y">Yu Bai</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+C">Cunshi Wang</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+M">Mengwei Qu</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+Z">Ziteng Lu</a>, <a href="/search/cs?searchtype=author&query=Soria%2C+R">Roberto Soria</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jifeng Liu</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="2404.10757v2-abstract-short" style="display: inline;"> Light curves serve as a valuable source of information on stellar formation and evolution. With the rapid advancement of machine learning techniques, it can be effectively processed to extract astronomical patterns and information. In this study, we present a comprehensive evaluation of deep-learning and large language model (LLM) based models for the automatic classification of variable star ligh… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.10757v2-abstract-full').style.display = 'inline'; document.getElementById('2404.10757v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.10757v2-abstract-full" style="display: none;"> Light curves serve as a valuable source of information on stellar formation and evolution. With the rapid advancement of machine learning techniques, it can be effectively processed to extract astronomical patterns and information. In this study, we present a comprehensive evaluation of deep-learning and large language model (LLM) based models for the automatic classification of variable star light curves, based on large datasets from the Kepler and K2 missions. Special emphasis is placed on Cepheids, RR Lyrae, and eclipsing binaries, examining the influence of observational cadence and phase distribution on classification precision. Employing AutoDL optimization, we achieve striking performance with the 1D-Convolution+BiLSTM architecture and the Swin Transformer, hitting accuracies of 94\% and 99\% correspondingly, with the latter demonstrating a notable 83\% accuracy in discerning the elusive Type II Cepheids-comprising merely 0.02\% of the total dataset.We unveil StarWhisper LightCurve (LC), an innovative Series comprising three LLM-based models: LLM, multimodal large language model (MLLM), and Large Audio Language Model (LALM). Each model is fine-tuned with strategic prompt engineering and customized training methods to explore the emergent abilities of these models for astronomical data. Remarkably, StarWhisper LC Series exhibit high accuracies around 90\%, significantly reducing the need for explicit feature engineering, thereby paving the way for streamlined parallel data processing and the progression of multifaceted multimodal models in astronomical applications. The study furnishes two detailed catalogs illustrating the impacts of phase and sampling intervals on deep learning classification accuracy, showing that a substantial decrease of up to 14\% in observation duration and 21\% in sampling points can be realized without compromising accuracy by more than 10\%. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.10757v2-abstract-full').style.display = 'none'; document.getElementById('2404.10757v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 16 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">35 pages, 20 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.04247">arXiv:2402.04247</a> <span> [<a href="https://arxiv.org/pdf/2402.04247">pdf</a>, <a href="https://arxiv.org/format/2402.04247">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Prioritizing Safeguarding Over Autonomy: Risks of LLM Agents for Science </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tang%2C+X">Xiangru Tang</a>, <a href="/search/cs?searchtype=author&query=Jin%2C+Q">Qiao Jin</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+K">Kunlun Zhu</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+T">Tongxin Yuan</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yichi Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+W">Wangchunshu Zhou</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meng Qu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Y">Yilun Zhao</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jian Tang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhuosheng Zhang</a>, <a href="/search/cs?searchtype=author&query=Cohan%2C+A">Arman Cohan</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+Z">Zhiyong Lu</a>, <a href="/search/cs?searchtype=author&query=Gerstein%2C+M">Mark Gerstein</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="2402.04247v4-abstract-short" style="display: inline;"> Intelligent agents powered by large language models (LLMs) have demonstrated substantial promise in autonomously conducting experiments and facilitating scientific discoveries across various disciplines. While their capabilities are promising, these agents, called scientific LLM agents, also introduce novel vulnerabilities that demand careful consideration for safety. However, there exists a notab… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.04247v4-abstract-full').style.display = 'inline'; document.getElementById('2402.04247v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.04247v4-abstract-full" style="display: none;"> Intelligent agents powered by large language models (LLMs) have demonstrated substantial promise in autonomously conducting experiments and facilitating scientific discoveries across various disciplines. While their capabilities are promising, these agents, called scientific LLM agents, also introduce novel vulnerabilities that demand careful consideration for safety. However, there exists a notable gap in the literature, as there has been no comprehensive exploration of these vulnerabilities. This perspective paper fills this gap by conducting a thorough examination of vulnerabilities in LLM-based agents within scientific domains, shedding light on potential risks associated with their misuse and emphasizing the need for safety measures. We begin by providing a comprehensive overview of the potential risks inherent to scientific LLM agents, taking into account user intent, the specific scientific domain, and their potential impact on the external environment. Then, we delve into the origins of these vulnerabilities and provide a scoping review of the limited existing works. Based on our analysis, we propose a triadic framework involving human regulation, agent alignment, and an understanding of environmental feedback (agent regulation) to mitigate these identified risks. Furthermore, we highlight the limitations and challenges associated with safeguarding scientific agents and advocate for the development of improved models, robust benchmarks, and comprehensive regulations to address these issues effectively. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.04247v4-abstract-full').style.display = 'none'; document.getElementById('2402.04247v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 June, 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/2310.17290">arXiv:2310.17290</a> <span> [<a href="https://arxiv.org/pdf/2310.17290">pdf</a>, <a href="https://arxiv.org/format/2310.17290">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> RIO: A Benchmark for Reasoning Intention-Oriented Objects in Open Environments </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Qu%2C+M">Mengxue Qu</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yu Wu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+W">Wu Liu</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+X">Xiaodan Liang</a>, <a href="/search/cs?searchtype=author&query=Song%2C+J">Jingkuan Song</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Y">Yao Zhao</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+Y">Yunchao Wei</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="2310.17290v1-abstract-short" style="display: inline;"> Intention-oriented object detection aims to detect desired objects based on specific intentions or requirements. For instance, when we desire to "lie down and rest", we instinctively seek out a suitable option such as a "bed" or a "sofa" that can fulfill our needs. Previous work in this area is limited either by the number of intention descriptions or by the affordance vocabulary available for int… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.17290v1-abstract-full').style.display = 'inline'; document.getElementById('2310.17290v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.17290v1-abstract-full" style="display: none;"> Intention-oriented object detection aims to detect desired objects based on specific intentions or requirements. For instance, when we desire to "lie down and rest", we instinctively seek out a suitable option such as a "bed" or a "sofa" that can fulfill our needs. Previous work in this area is limited either by the number of intention descriptions or by the affordance vocabulary available for intention objects. These limitations make it challenging to handle intentions in open environments effectively. To facilitate this research, we construct a comprehensive dataset called Reasoning Intention-Oriented Objects (RIO). In particular, RIO is specifically designed to incorporate diverse real-world scenarios and a wide range of object categories. It offers the following key features: 1) intention descriptions in RIO are represented as natural sentences rather than a mere word or verb phrase, making them more practical and meaningful; 2) the intention descriptions are contextually relevant to the scene, enabling a broader range of potential functionalities associated with the objects; 3) the dataset comprises a total of 40,214 images and 130,585 intention-object pairs. With the proposed RIO, we evaluate the ability of some existing models to reason intention-oriented objects in open environments. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.17290v1-abstract-full').style.display = 'none'; document.getElementById('2310.17290v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 October, 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">NeurIPS 2023 D&B accepted. See our project page for more details: https://reasonio.github.io/</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.01089">arXiv:2310.01089</a> <span> [<a href="https://arxiv.org/pdf/2310.01089">pdf</a>, <a href="https://arxiv.org/format/2310.01089">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"> GraphText: Graph Reasoning in Text Space </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhao%2C+J">Jianan Zhao</a>, <a href="/search/cs?searchtype=author&query=Zhuo%2C+L">Le Zhuo</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+Y">Yikang Shen</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meng Qu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+K">Kai Liu</a>, <a href="/search/cs?searchtype=author&query=Bronstein%2C+M">Michael Bronstein</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Z">Zhaocheng Zhu</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jian Tang</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="2310.01089v1-abstract-short" style="display: inline;"> Large Language Models (LLMs) have gained the ability to assimilate human knowledge and facilitate natural language interactions with both humans and other LLMs. However, despite their impressive achievements, LLMs have not made significant advancements in the realm of graph machine learning. This limitation arises because graphs encapsulate distinct relational data, making it challenging to transf… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.01089v1-abstract-full').style.display = 'inline'; document.getElementById('2310.01089v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.01089v1-abstract-full" style="display: none;"> Large Language Models (LLMs) have gained the ability to assimilate human knowledge and facilitate natural language interactions with both humans and other LLMs. However, despite their impressive achievements, LLMs have not made significant advancements in the realm of graph machine learning. This limitation arises because graphs encapsulate distinct relational data, making it challenging to transform them into natural language that LLMs understand. In this paper, we bridge this gap with a novel framework, GraphText, that translates graphs into natural language. GraphText derives a graph-syntax tree for each graph that encapsulates both the node attributes and inter-node relationships. Traversal of the tree yields a graph text sequence, which is then processed by an LLM to treat graph tasks as text generation tasks. Notably, GraphText offers multiple advantages. It introduces training-free graph reasoning: even without training on graph data, GraphText with ChatGPT can achieve on par with, or even surpassing, the performance of supervised-trained graph neural networks through in-context learning (ICL). Furthermore, GraphText paves the way for interactive graph reasoning, allowing both humans and LLMs to communicate with the model seamlessly using natural language. These capabilities underscore the vast, yet-to-be-explored potential of LLMs in the domain of graph machine learning. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.01089v1-abstract-full').style.display = 'none'; document.getElementById('2310.01089v1-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 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">Preprint. Work in progress</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2304.11688">arXiv:2304.11688</a> <span> [<a href="https://arxiv.org/pdf/2304.11688">pdf</a>, <a href="https://arxiv.org/format/2304.11688">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 Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> TGNN: A Joint Semi-supervised Framework for Graph-level Classification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ju%2C+W">Wei Ju</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+X">Xiao Luo</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meng Qu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yifan Wang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Chong Chen</a>, <a href="/search/cs?searchtype=author&query=Deng%2C+M">Minghua Deng</a>, <a href="/search/cs?searchtype=author&query=Hua%2C+X">Xian-Sheng Hua</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+M">Ming 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="2304.11688v1-abstract-short" style="display: inline;"> This paper studies semi-supervised graph classification, a crucial task with a wide range of applications in social network analysis and bioinformatics. Recent works typically adopt graph neural networks to learn graph-level representations for classification, failing to explicitly leverage features derived from graph topology (e.g., paths). Moreover, when labeled data is scarce, these methods are… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.11688v1-abstract-full').style.display = 'inline'; document.getElementById('2304.11688v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2304.11688v1-abstract-full" style="display: none;"> This paper studies semi-supervised graph classification, a crucial task with a wide range of applications in social network analysis and bioinformatics. Recent works typically adopt graph neural networks to learn graph-level representations for classification, failing to explicitly leverage features derived from graph topology (e.g., paths). Moreover, when labeled data is scarce, these methods are far from satisfactory due to their insufficient topology exploration of unlabeled data. We address the challenge by proposing a novel semi-supervised framework called Twin Graph Neural Network (TGNN). To explore graph structural information from complementary views, our TGNN has a message passing module and a graph kernel module. To fully utilize unlabeled data, for each module, we calculate the similarity of each unlabeled graph to other labeled graphs in the memory bank and our consistency loss encourages consistency between two similarity distributions in different embedding spaces. The two twin modules collaborate with each other by exchanging instance similarity knowledge to fully explore the structure information of both labeled and unlabeled data. We evaluate our TGNN on various public datasets and show that it achieves strong performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.11688v1-abstract-full').style.display = 'none'; document.getElementById('2304.11688v1-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, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 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 Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence (IJCAI 2022)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2304.03928">arXiv:2304.03928</a> <span> [<a href="https://arxiv.org/pdf/2304.03928">pdf</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="Applications">stat.AP</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1039/D3NR02322B">10.1039/D3NR02322B <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Interpretable machine learning-accelerated seed treatment by nanomaterials for environmental stress alleviation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yu%2C+H">Hengjie Yu</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+D">Dan Luo</a>, <a href="/search/cs?searchtype=author&query=Li%2C+S+F+Y">Sam F. Y. Li</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+M">Maozhen Qu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+D">Da Liu</a>, <a href="/search/cs?searchtype=author&query=He%2C+Y">Yingchao He</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+F">Fang Cheng</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="2304.03928v1-abstract-short" style="display: inline;"> Crops are constantly challenged by different environmental conditions. Seed treatment by nanomaterials is a cost-effective and environmentally-friendly solution for environmental stress mitigation in crop plants. Here, 56 seed nanopriming treatments are used to alleviate environmental stresses in maize. Seven selected nanopriming treatments significantly increase the stress resistance index (SRI)… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.03928v1-abstract-full').style.display = 'inline'; document.getElementById('2304.03928v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2304.03928v1-abstract-full" style="display: none;"> Crops are constantly challenged by different environmental conditions. Seed treatment by nanomaterials is a cost-effective and environmentally-friendly solution for environmental stress mitigation in crop plants. Here, 56 seed nanopriming treatments are used to alleviate environmental stresses in maize. Seven selected nanopriming treatments significantly increase the stress resistance index (SRI) by 13.9% and 12.6% under salinity stress and combined heat-drought stress, respectively. Metabolomics data reveals that ZnO nanopriming treatment, with the highest SRI value, mainly regulates the pathways of amino acid metabolism, secondary metabolite synthesis, carbohydrate metabolism, and translation. Understanding the mechanism of seed nanopriming is still difficult due to the variety of nanomaterials and the complexity of interactions between nanomaterials and plants. Using the nanopriming data, we present an interpretable structure-activity relationship (ISAR) approach based on interpretable machine learning for predicting and understanding its stress mitigation effects. The post hoc and model-based interpretation approaches of machine learning are combined to provide complementary benefits and give researchers or policymakers more illuminating or trustworthy results. The concentration, size, and zeta potential of nanoparticles are identified as dominant factors for correlating root dry weight under salinity stress, and their effects and interactions are explained. Additionally, a web-based interactive tool is developed for offering prediction-level interpretation and gathering more details about specific nanopriming treatments. This work offers a promising framework for accelerating the agricultural applications of nanomaterials and may profoundly contribute to nanosafety assessment. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.03928v1-abstract-full').style.display = 'none'; document.getElementById('2304.03928v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 April, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">30 pages, 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/2210.14709">arXiv:2210.14709</a> <span> [<a href="https://arxiv.org/pdf/2210.14709">pdf</a>, <a href="https://arxiv.org/format/2210.14709">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"> Learning on Large-scale Text-attributed Graphs via Variational Inference </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhao%2C+J">Jianan Zhao</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meng Qu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+C">Chaozhuo Li</a>, <a href="/search/cs?searchtype=author&query=Yan%2C+H">Hao Yan</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qian Liu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+R">Rui Li</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+X">Xing Xie</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jian Tang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2210.14709v2-abstract-short" style="display: inline;"> This paper studies learning on text-attributed graphs (TAGs), where each node is associated with a text description. An ideal solution for such a problem would be integrating both the text and graph structure information with large language models and graph neural networks (GNNs). However, the problem becomes very challenging when graphs are large due to the high computational complexity brought b… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.14709v2-abstract-full').style.display = 'inline'; document.getElementById('2210.14709v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2210.14709v2-abstract-full" style="display: none;"> This paper studies learning on text-attributed graphs (TAGs), where each node is associated with a text description. An ideal solution for such a problem would be integrating both the text and graph structure information with large language models and graph neural networks (GNNs). However, the problem becomes very challenging when graphs are large due to the high computational complexity brought by training large language models and GNNs together. In this paper, we propose an efficient and effective solution to learning on large text-attributed graphs by fusing graph structure and language learning with a variational Expectation-Maximization (EM) framework, called GLEM. Instead of simultaneously training large language models and GNNs on big graphs, GLEM proposes to alternatively update the two modules in the E-step and M-step. Such a procedure allows training the two modules separately while simultaneously allowing the two modules to interact and mutually enhance each other. Extensive experiments on multiple data sets demonstrate the efficiency and effectiveness of the proposed approach. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.14709v2-abstract-full').style.display = 'none'; document.getElementById('2210.14709v2-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 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 26 October, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">ICLR 2023</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2207.13325">arXiv:2207.13325</a> <span> [<a href="https://arxiv.org/pdf/2207.13325">pdf</a>, <a href="https://arxiv.org/format/2207.13325">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> SiRi: A Simple Selective Retraining Mechanism for Transformer-based Visual Grounding </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Qu%2C+M">Mengxue Qu</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yu Wu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+W">Wu Liu</a>, <a href="/search/cs?searchtype=author&query=Gong%2C+Q">Qiqi Gong</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+X">Xiaodan Liang</a>, <a href="/search/cs?searchtype=author&query=Russakovsky%2C+O">Olga Russakovsky</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Y">Yao Zhao</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+Y">Yunchao Wei</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="2207.13325v1-abstract-short" style="display: inline;"> In this paper, we investigate how to achieve better visual grounding with modern vision-language transformers, and propose a simple yet powerful Selective Retraining (SiRi) mechanism for this challenging task. Particularly, SiRi conveys a significant principle to the research of visual grounding, i.e., a better initialized vision-language encoder would help the model converge to a better local min… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.13325v1-abstract-full').style.display = 'inline'; document.getElementById('2207.13325v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2207.13325v1-abstract-full" style="display: none;"> In this paper, we investigate how to achieve better visual grounding with modern vision-language transformers, and propose a simple yet powerful Selective Retraining (SiRi) mechanism for this challenging task. Particularly, SiRi conveys a significant principle to the research of visual grounding, i.e., a better initialized vision-language encoder would help the model converge to a better local minimum, advancing the performance accordingly. In specific, we continually update the parameters of the encoder as the training goes on, while periodically re-initialize rest of the parameters to compel the model to be better optimized based on an enhanced encoder. SiRi can significantly outperform previous approaches on three popular benchmarks. Specifically, our method achieves 83.04% Top1 accuracy on RefCOCO+ testA, outperforming the state-of-the-art approaches (training from scratch) by more than 10.21%. Additionally, we reveal that SiRi performs surprisingly superior even with limited training data. We also extend it to transformer-based visual grounding models and other vision-language tasks to verify the validity. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.13325v1-abstract-full').style.display = 'none'; document.getElementById('2207.13325v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 July, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">21 pages (including Supplementary Materials); Accepted to ECCV 2022</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2205.10550">arXiv:2205.10550</a> <span> [<a href="https://arxiv.org/pdf/2205.10550">pdf</a>, <a href="https://arxiv.org/format/2205.10550">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 Retrieval">cs.IR</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1145/3488560.3498429">10.1145/3488560.3498429 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> KGNN: Harnessing Kernel-based Networks for Semi-supervised Graph Classification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ju%2C+W">Wei Ju</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+J">Junwei Yang</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meng Qu</a>, <a href="/search/cs?searchtype=author&query=Song%2C+W">Weiping Song</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+J">Jianhao Shen</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+M">Ming 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="2205.10550v1-abstract-short" style="display: inline;"> This paper studies semi-supervised graph classification, which is an important problem with various applications in social network analysis and bioinformatics. This problem is typically solved by using graph neural networks (GNNs), which yet rely on a large number of labeled graphs for training and are unable to leverage unlabeled graphs. We address the limitations by proposing the Kernel-based Gr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.10550v1-abstract-full').style.display = 'inline'; document.getElementById('2205.10550v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2205.10550v1-abstract-full" style="display: none;"> This paper studies semi-supervised graph classification, which is an important problem with various applications in social network analysis and bioinformatics. This problem is typically solved by using graph neural networks (GNNs), which yet rely on a large number of labeled graphs for training and are unable to leverage unlabeled graphs. We address the limitations by proposing the Kernel-based Graph Neural Network (KGNN). A KGNN consists of a GNN-based network as well as a kernel-based network parameterized by a memory network. The GNN-based network performs classification through learning graph representations to implicitly capture the similarity between query graphs and labeled graphs, while the kernel-based network uses graph kernels to explicitly compare each query graph with all the labeled graphs stored in a memory for prediction. The two networks are motivated from complementary perspectives, and thus combing them allows KGNN to use labeled graphs more effectively. We jointly train the two networks by maximizing their agreement on unlabeled graphs via posterior regularization, so that the unlabeled graphs serve as a bridge to let both networks mutually enhance each other. Experiments on a range of well-known benchmark datasets demonstrate that KGNN achieves impressive performance over competitive baselines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.10550v1-abstract-full').style.display = 'none'; document.getElementById('2205.10550v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 May, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Published as a full paper at WSDM 2022</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2204.12736">arXiv:2204.12736</a> <span> [<a href="https://arxiv.org/pdf/2204.12736">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1007/978-3-031-20868-3_25">10.1007/978-3-031-20868-3_25 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> A Multi-Head Convolutional Neural Network With Multi-path Attention improves Image Denoising </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jiahong Zhang</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meijun Qu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Ye Wang</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+L">Lihong Cao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2204.12736v2-abstract-short" style="display: inline;"> Recently, convolutional neural networks (CNNs) and attention mechanisms have been widely used in image denoising and achieved satisfactory performance. However, the previous works mostly use a single head to receive the noisy image, limiting the richness of extracted features. Therefore, a novel CNN with multiple heads (MH) named MHCNN is proposed in this paper, whose heads will receive the input… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2204.12736v2-abstract-full').style.display = 'inline'; document.getElementById('2204.12736v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2204.12736v2-abstract-full" style="display: none;"> Recently, convolutional neural networks (CNNs) and attention mechanisms have been widely used in image denoising and achieved satisfactory performance. However, the previous works mostly use a single head to receive the noisy image, limiting the richness of extracted features. Therefore, a novel CNN with multiple heads (MH) named MHCNN is proposed in this paper, whose heads will receive the input images rotated by different rotation angles. MH makes MHCNN simultaneously utilize features of rotated images to remove noise. To integrate these features effectively, we present a novel multi-path attention mechanism (MPA). Unlike previous attention mechanisms that handle pixel-level, channel-level, or patch-level features, MPA focuses on features at the image level. Experiments show MHCNN surpasses other state-of-the-art CNN models on additive white Gaussian noise (AWGN) denoising and real-world image denoising. Its peak signal-to-noise ratio (PSNR) results are higher than other networks, such as BRDNet, RIDNet, PAN-Net, and CSANN. The code is accessible at https://github.com/JiaHongZ/MHCNN. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2204.12736v2-abstract-full').style.display = 'none'; document.getElementById('2204.12736v2-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, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 27 April, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2204.07524">arXiv:2204.07524</a> <span> [<a href="https://arxiv.org/pdf/2204.07524">pdf</a>, <a href="https://arxiv.org/format/2204.07524">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"> Neural Structured Prediction for Inductive Node Classification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meng Qu</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+H">Huiyu Cai</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jian Tang</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="2204.07524v1-abstract-short" style="display: inline;"> This paper studies node classification in the inductive setting, i.e., aiming to learn a model on labeled training graphs and generalize it to infer node labels on unlabeled test graphs. This problem has been extensively studied with graph neural networks (GNNs) by learning effective node representations, as well as traditional structured prediction methods for modeling the structured output of no… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2204.07524v1-abstract-full').style.display = 'inline'; document.getElementById('2204.07524v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2204.07524v1-abstract-full" style="display: none;"> This paper studies node classification in the inductive setting, i.e., aiming to learn a model on labeled training graphs and generalize it to infer node labels on unlabeled test graphs. This problem has been extensively studied with graph neural networks (GNNs) by learning effective node representations, as well as traditional structured prediction methods for modeling the structured output of node labels, e.g., conditional random fields (CRFs). In this paper, we present a new approach called the Structured Proxy Network (SPN), which combines the advantages of both worlds. SPN defines flexible potential functions of CRFs with GNNs. However, learning such a model is nontrivial as it involves optimizing a maximin game with high-cost inference. Inspired by the underlying connection between joint and marginal distributions defined by Markov networks, we propose to solve an approximate version of the optimization problem as a proxy, which yields a near-optimal solution, making learning more efficient. Extensive experiments on two settings show that our approach outperforms many competitive baselines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2204.07524v1-abstract-full').style.display = 'none'; document.getElementById('2204.07524v1-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 April, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">iclr 2022</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2203.04695">arXiv:2203.04695</a> <span> [<a href="https://arxiv.org/pdf/2203.04695">pdf</a>, <a href="https://arxiv.org/format/2203.04695">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Biomolecules">q-bio.BM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Structured Multi-task Learning for Molecular Property Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+S">Shengchao Liu</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meng Qu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zuobai Zhang</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+H">Huiyu Cai</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jian Tang</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="2203.04695v2-abstract-short" style="display: inline;"> Multi-task learning for molecular property prediction is becoming increasingly important in drug discovery. However, in contrast to other domains, the performance of multi-task learning in drug discovery is still not satisfying as the number of labeled data for each task is too limited, which calls for additional data to complement the data scarcity. In this paper, we study multi-task learning for… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.04695v2-abstract-full').style.display = 'inline'; document.getElementById('2203.04695v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2203.04695v2-abstract-full" style="display: none;"> Multi-task learning for molecular property prediction is becoming increasingly important in drug discovery. However, in contrast to other domains, the performance of multi-task learning in drug discovery is still not satisfying as the number of labeled data for each task is too limited, which calls for additional data to complement the data scarcity. In this paper, we study multi-task learning for molecular property prediction in a novel setting, where a relation graph between tasks is available. We first construct a dataset (ChEMBL-STRING) including around 400 tasks as well as a task relation graph. Then to better utilize such relation graph, we propose a method called SGNN-EBM to systematically investigate the structured task modeling from two perspectives. (1) In the \emph{latent} space, we model the task representations by applying a state graph neural network (SGNN) on the relation graph. (2) In the \emph{output} space, we employ structured prediction with the energy-based model (EBM), which can be efficiently trained through noise-contrastive estimation (NCE) approach. Empirical results justify the effectiveness of SGNN-EBM. Code is available on https://github.com/chao1224/SGNN-EBM. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.04695v2-abstract-full').style.display = 'none'; document.getElementById('2203.04695v2-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 October, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 February, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2202.08320">arXiv:2202.08320</a> <span> [<a href="https://arxiv.org/pdf/2202.08320">pdf</a>, <a href="https://arxiv.org/format/2202.08320">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"> TorchDrug: A Powerful and Flexible Machine Learning Platform for Drug Discovery </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhu%2C+Z">Zhaocheng Zhu</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+C">Chence Shi</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zuobai Zhang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+S">Shengchao Liu</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+M">Minghao Xu</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+X">Xinyu Yuan</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yangtian Zhang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+J">Junkun Chen</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+H">Huiyu Cai</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+J">Jiarui Lu</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+C">Chang Ma</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+R">Runcheng Liu</a>, <a href="/search/cs?searchtype=author&query=Xhonneux%2C+L">Louis-Pascal Xhonneux</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meng Qu</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jian Tang</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="2202.08320v1-abstract-short" style="display: inline;"> Machine learning has huge potential to revolutionize the field of drug discovery and is attracting increasing attention in recent years. However, lacking domain knowledge (e.g., which tasks to work on), standard benchmarks and data preprocessing pipelines are the main obstacles for machine learning researchers to work in this domain. To facilitate the progress of machine learning for drug discover… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2202.08320v1-abstract-full').style.display = 'inline'; document.getElementById('2202.08320v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2202.08320v1-abstract-full" style="display: none;"> Machine learning has huge potential to revolutionize the field of drug discovery and is attracting increasing attention in recent years. However, lacking domain knowledge (e.g., which tasks to work on), standard benchmarks and data preprocessing pipelines are the main obstacles for machine learning researchers to work in this domain. To facilitate the progress of machine learning for drug discovery, we develop TorchDrug, a powerful and flexible machine learning platform for drug discovery built on top of PyTorch. TorchDrug benchmarks a variety of important tasks in drug discovery, including molecular property prediction, pretrained molecular representations, de novo molecular design and optimization, retrosynthsis prediction, and biomedical knowledge graph reasoning. State-of-the-art techniques based on geometric deep learning (or graph machine learning), deep generative models, reinforcement learning and knowledge graph reasoning are implemented for these tasks. TorchDrug features a hierarchical interface that facilitates customization from both novices and experts in this domain. Tutorials, benchmark results and documentation are available at https://torchdrug.ai. Code is released under Apache License 2.0. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2202.08320v1-abstract-full').style.display = 'none'; document.getElementById('2202.08320v1-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 February, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2010.16004">arXiv:2010.16004</a> <span> [<a href="https://arxiv.org/pdf/2010.16004">pdf</a>, <a href="https://arxiv.org/format/2010.16004">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multiagent Systems">cs.MA</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"> COVI-AgentSim: an Agent-based Model for Evaluating Methods of Digital Contact Tracing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gupta%2C+P">Prateek Gupta</a>, <a href="/search/cs?searchtype=author&query=Maharaj%2C+T">Tegan Maharaj</a>, <a href="/search/cs?searchtype=author&query=Weiss%2C+M">Martin Weiss</a>, <a href="/search/cs?searchtype=author&query=Rahaman%2C+N">Nasim Rahaman</a>, <a href="/search/cs?searchtype=author&query=Alsdurf%2C+H">Hannah Alsdurf</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+A">Abhinav Sharma</a>, <a href="/search/cs?searchtype=author&query=Minoyan%2C+N">Nanor Minoyan</a>, <a href="/search/cs?searchtype=author&query=Harnois-Leblanc%2C+S">Soren Harnois-Leblanc</a>, <a href="/search/cs?searchtype=author&query=Schmidt%2C+V">Victor Schmidt</a>, <a href="/search/cs?searchtype=author&query=Charles%2C+P+S">Pierre-Luc St. Charles</a>, <a href="/search/cs?searchtype=author&query=Deleu%2C+T">Tristan Deleu</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+A">Andrew Williams</a>, <a href="/search/cs?searchtype=author&query=Patel%2C+A">Akshay Patel</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meng Qu</a>, <a href="/search/cs?searchtype=author&query=Bilaniuk%2C+O">Olexa Bilaniuk</a>, <a href="/search/cs?searchtype=author&query=Caron%2C+G+M">Ga茅tan Marceau Caron</a>, <a href="/search/cs?searchtype=author&query=Carrier%2C+P+L">Pierre Luc Carrier</a>, <a href="/search/cs?searchtype=author&query=Ortiz-Gagn%C3%A9%2C+S">Satya Ortiz-Gagn茅</a>, <a href="/search/cs?searchtype=author&query=Rousseau%2C+M">Marc-Andre Rousseau</a>, <a href="/search/cs?searchtype=author&query=Buckeridge%2C+D">David Buckeridge</a>, <a href="/search/cs?searchtype=author&query=Ghosn%2C+J">Joumana Ghosn</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yang Zhang</a>, <a href="/search/cs?searchtype=author&query=Sch%C3%B6lkopf%2C+B">Bernhard Sch枚lkopf</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jian Tang</a>, <a href="/search/cs?searchtype=author&query=Rish%2C+I">Irina Rish</a> , et al. (4 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2010.16004v1-abstract-short" style="display: inline;"> The rapid global spread of COVID-19 has led to an unprecedented demand for effective methods to mitigate the spread of the disease, and various digital contact tracing (DCT) methods have emerged as a component of the solution. In order to make informed public health choices, there is a need for tools which allow evaluation and comparison of DCT methods. We introduce an agent-based compartmental si… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2010.16004v1-abstract-full').style.display = 'inline'; document.getElementById('2010.16004v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2010.16004v1-abstract-full" style="display: none;"> The rapid global spread of COVID-19 has led to an unprecedented demand for effective methods to mitigate the spread of the disease, and various digital contact tracing (DCT) methods have emerged as a component of the solution. In order to make informed public health choices, there is a need for tools which allow evaluation and comparison of DCT methods. We introduce an agent-based compartmental simulator we call COVI-AgentSim, integrating detailed consideration of virology, disease progression, social contact networks, and mobility patterns, based on parameters derived from empirical research. We verify by comparing to real data that COVI-AgentSim is able to reproduce realistic COVID-19 spread dynamics, and perform a sensitivity analysis to verify that the relative performance of contact tracing methods are consistent across a range of settings. We use COVI-AgentSim to perform cost-benefit analyses comparing no DCT to: 1) standard binary contact tracing (BCT) that assigns binary recommendations based on binary test results; and 2) a rule-based method for feature-based contact tracing (FCT) that assigns a graded level of recommendation based on diverse individual features. We find all DCT methods consistently reduce the spread of the disease, and that the advantage of FCT over BCT is maintained over a wide range of adoption rates. Feature-based methods of contact tracing avert more disability-adjusted life years (DALYs) per socioeconomic cost (measured by productive hours lost). Our results suggest any DCT method can help save lives, support re-opening of economies, and prevent second-wave outbreaks, and that FCT methods are a promising direction for enriching BCT using self-reported symptoms, yielding earlier warning signals and a significantly reduced spread of the virus per socioeconomic cost. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2010.16004v1-abstract-full').style.display = 'none'; document.getElementById('2010.16004v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 October, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2010.12536">arXiv:2010.12536</a> <span> [<a href="https://arxiv.org/pdf/2010.12536">pdf</a>, <a href="https://arxiv.org/format/2010.12536">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="Multiagent Systems">cs.MA</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"> Predicting Infectiousness for Proactive Contact Tracing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bengio%2C+Y">Yoshua Bengio</a>, <a href="/search/cs?searchtype=author&query=Gupta%2C+P">Prateek Gupta</a>, <a href="/search/cs?searchtype=author&query=Maharaj%2C+T">Tegan Maharaj</a>, <a href="/search/cs?searchtype=author&query=Rahaman%2C+N">Nasim Rahaman</a>, <a href="/search/cs?searchtype=author&query=Weiss%2C+M">Martin Weiss</a>, <a href="/search/cs?searchtype=author&query=Deleu%2C+T">Tristan Deleu</a>, <a href="/search/cs?searchtype=author&query=Muller%2C+E">Eilif Muller</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meng Qu</a>, <a href="/search/cs?searchtype=author&query=Schmidt%2C+V">Victor Schmidt</a>, <a href="/search/cs?searchtype=author&query=St-Charles%2C+P">Pierre-Luc St-Charles</a>, <a href="/search/cs?searchtype=author&query=Alsdurf%2C+H">Hannah Alsdurf</a>, <a href="/search/cs?searchtype=author&query=Bilanuik%2C+O">Olexa Bilanuik</a>, <a href="/search/cs?searchtype=author&query=Buckeridge%2C+D">David Buckeridge</a>, <a href="/search/cs?searchtype=author&query=Caron%2C+G+M">G谩etan Marceau Caron</a>, <a href="/search/cs?searchtype=author&query=Carrier%2C+P">Pierre-Luc Carrier</a>, <a href="/search/cs?searchtype=author&query=Ghosn%2C+J">Joumana Ghosn</a>, <a href="/search/cs?searchtype=author&query=Ortiz-Gagne%2C+S">Satya Ortiz-Gagne</a>, <a href="/search/cs?searchtype=author&query=Pal%2C+C">Chris Pal</a>, <a href="/search/cs?searchtype=author&query=Rish%2C+I">Irina Rish</a>, <a href="/search/cs?searchtype=author&query=Sch%C3%B6lkopf%2C+B">Bernhard Sch枚lkopf</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+A">Abhinav Sharma</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jian Tang</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+A">Andrew Williams</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2010.12536v1-abstract-short" style="display: inline;"> The COVID-19 pandemic has spread rapidly worldwide, overwhelming manual contact tracing in many countries and resulting in widespread lockdowns for emergency containment. Large-scale digital contact tracing (DCT) has emerged as a potential solution to resume economic and social activity while minimizing spread of the virus. Various DCT methods have been proposed, each making trade-offs between pri… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2010.12536v1-abstract-full').style.display = 'inline'; document.getElementById('2010.12536v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2010.12536v1-abstract-full" style="display: none;"> The COVID-19 pandemic has spread rapidly worldwide, overwhelming manual contact tracing in many countries and resulting in widespread lockdowns for emergency containment. Large-scale digital contact tracing (DCT) has emerged as a potential solution to resume economic and social activity while minimizing spread of the virus. Various DCT methods have been proposed, each making trade-offs between privacy, mobility restrictions, and public health. The most common approach, binary contact tracing (BCT), models infection as a binary event, informed only by an individual's test results, with corresponding binary recommendations that either all or none of the individual's contacts quarantine. BCT ignores the inherent uncertainty in contacts and the infection process, which could be used to tailor messaging to high-risk individuals, and prompt proactive testing or earlier warnings. It also does not make use of observations such as symptoms or pre-existing medical conditions, which could be used to make more accurate infectiousness predictions. In this paper, we use a recently-proposed COVID-19 epidemiological simulator to develop and test methods that can be deployed to a smartphone to locally and proactively predict an individual's infectiousness (risk of infecting others) based on their contact history and other information, while respecting strong privacy constraints. Predictions are used to provide personalized recommendations to the individual via an app, as well as to send anonymized messages to the individual's contacts, who use this information to better predict their own infectiousness, an approach we call proactive contact tracing (PCT). We find a deep-learning based PCT method which improves over BCT for equivalent average mobility, suggesting PCT could help in safe re-opening and second-wave prevention. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2010.12536v1-abstract-full').style.display = 'none'; document.getElementById('2010.12536v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 October, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2010.04029">arXiv:2010.04029</a> <span> [<a href="https://arxiv.org/pdf/2010.04029">pdf</a>, <a href="https://arxiv.org/format/2010.04029">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"> RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meng Qu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+J">Junkun Chen</a>, <a href="/search/cs?searchtype=author&query=Xhonneux%2C+L">Louis-Pascal Xhonneux</a>, <a href="/search/cs?searchtype=author&query=Bengio%2C+Y">Yoshua Bengio</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jian Tang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2010.04029v2-abstract-short" style="display: inline;"> This paper studies learning logic rules for reasoning on knowledge graphs. Logic rules provide interpretable explanations when used for prediction as well as being able to generalize to other tasks, and hence are critical to learn. Existing methods either suffer from the problem of searching in a large search space (e.g., neural logic programming) or ineffective optimization due to sparse rewards… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2010.04029v2-abstract-full').style.display = 'inline'; document.getElementById('2010.04029v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2010.04029v2-abstract-full" style="display: none;"> This paper studies learning logic rules for reasoning on knowledge graphs. Logic rules provide interpretable explanations when used for prediction as well as being able to generalize to other tasks, and hence are critical to learn. Existing methods either suffer from the problem of searching in a large search space (e.g., neural logic programming) or ineffective optimization due to sparse rewards (e.g., techniques based on reinforcement learning). To address these limitations, this paper proposes a probabilistic model called RNNLogic. RNNLogic treats logic rules as a latent variable, and simultaneously trains a rule generator as well as a reasoning predictor with logic rules. We develop an EM-based algorithm for optimization. In each iteration, the reasoning predictor is first updated to explore some generated logic rules for reasoning. Then in the E-step, we select a set of high-quality rules from all generated rules with both the rule generator and reasoning predictor via posterior inference; and in the M-step, the rule generator is updated with the rules selected in the E-step. Experiments on four datasets prove the effectiveness of RNNLogic. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2010.04029v2-abstract-full').style.display = 'none'; document.getElementById('2010.04029v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 July, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 8 October, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2020. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">iclr 2021</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2007.02387">arXiv:2007.02387</a> <span> [<a href="https://arxiv.org/pdf/2007.02387">pdf</a>, <a href="https://arxiv.org/format/2007.02387">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Few-shot Relation Extraction via Bayesian Meta-learning on Relation Graphs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meng Qu</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+T">Tianyu Gao</a>, <a href="/search/cs?searchtype=author&query=Xhonneux%2C+L+A+C">Louis-Pascal A. C. Xhonneux</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jian Tang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2007.02387v1-abstract-short" style="display: inline;"> This paper studies few-shot relation extraction, which aims at predicting the relation for a pair of entities in a sentence by training with a few labeled examples in each relation. To more effectively generalize to new relations, in this paper we study the relationships between different relations and propose to leverage a global relation graph. We propose a novel Bayesian meta-learning approach… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2007.02387v1-abstract-full').style.display = 'inline'; document.getElementById('2007.02387v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2007.02387v1-abstract-full" style="display: none;"> This paper studies few-shot relation extraction, which aims at predicting the relation for a pair of entities in a sentence by training with a few labeled examples in each relation. To more effectively generalize to new relations, in this paper we study the relationships between different relations and propose to leverage a global relation graph. We propose a novel Bayesian meta-learning approach to effectively learn the posterior distribution of the prototype vectors of relations, where the initial prior of the prototype vectors is parameterized with a graph neural network on the global relation graph. Moreover, to effectively optimize the posterior distribution of the prototype vectors, we propose to use the stochastic gradient Langevin dynamics, which is related to the MAML algorithm but is able to handle the uncertainty of the prototype vectors. The whole framework can be effectively and efficiently optimized in an end-to-end fashion. Experiments on two benchmark datasets prove the effectiveness of our proposed approach against competitive baselines in both the few-shot and zero-shot settings. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2007.02387v1-abstract-full').style.display = 'none'; document.getElementById('2007.02387v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 July, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2020. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">icml2020</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2006.13463">arXiv:2006.13463</a> <span> [<a href="https://arxiv.org/pdf/2006.13463">pdf</a>, <a href="https://arxiv.org/format/2006.13463">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="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Graph Policy Network for Transferable Active Learning on Graphs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hu%2C+S">Shengding Hu</a>, <a href="/search/cs?searchtype=author&query=Xiong%2C+Z">Zheng Xiong</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meng Qu</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+X">Xingdi Yuan</a>, <a href="/search/cs?searchtype=author&query=C%C3%B4t%C3%A9%2C+M">Marc-Alexandre C么t茅</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zhiyuan Liu</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jian Tang</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="2006.13463v2-abstract-short" style="display: inline;"> Graph neural networks (GNNs) have been attracting increasing popularity due to their simplicity and effectiveness in a variety of fields. However, a large number of labeled data is generally required to train these networks, which could be very expensive to obtain in some domains. In this paper, we study active learning for GNNs, i.e., how to efficiently label the nodes on a graph to reduce the an… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2006.13463v2-abstract-full').style.display = 'inline'; document.getElementById('2006.13463v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2006.13463v2-abstract-full" style="display: none;"> Graph neural networks (GNNs) have been attracting increasing popularity due to their simplicity and effectiveness in a variety of fields. However, a large number of labeled data is generally required to train these networks, which could be very expensive to obtain in some domains. In this paper, we study active learning for GNNs, i.e., how to efficiently label the nodes on a graph to reduce the annotation cost of training GNNs. We formulate the problem as a sequential decision process on graphs and train a GNN-based policy network with reinforcement learning to learn the optimal query strategy. By jointly training on several source graphs with full labels, we learn a transferable active learning policy which can directly generalize to unlabeled target graphs. Experimental results on multiple datasets from different domains prove the effectiveness of the learned policy in promoting active learning performance in both settings of transferring between graphs in the same domain and across different domains. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2006.13463v2-abstract-full').style.display = 'none'; document.getElementById('2006.13463v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 October, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 June, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2020. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.2 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2005.08502">arXiv:2005.08502</a> <span> [<a href="https://arxiv.org/pdf/2005.08502">pdf</a>, <a href="https://arxiv.org/format/2005.08502">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <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"> COVI White Paper </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Alsdurf%2C+H">Hannah Alsdurf</a>, <a href="/search/cs?searchtype=author&query=Belliveau%2C+E">Edmond Belliveau</a>, <a href="/search/cs?searchtype=author&query=Bengio%2C+Y">Yoshua Bengio</a>, <a href="/search/cs?searchtype=author&query=Deleu%2C+T">Tristan Deleu</a>, <a href="/search/cs?searchtype=author&query=Gupta%2C+P">Prateek Gupta</a>, <a href="/search/cs?searchtype=author&query=Ippolito%2C+D">Daphne Ippolito</a>, <a href="/search/cs?searchtype=author&query=Janda%2C+R">Richard Janda</a>, <a href="/search/cs?searchtype=author&query=Jarvie%2C+M">Max Jarvie</a>, <a href="/search/cs?searchtype=author&query=Kolody%2C+T">Tyler Kolody</a>, <a href="/search/cs?searchtype=author&query=Krastev%2C+S">Sekoul Krastev</a>, <a href="/search/cs?searchtype=author&query=Maharaj%2C+T">Tegan Maharaj</a>, <a href="/search/cs?searchtype=author&query=Obryk%2C+R">Robert Obryk</a>, <a href="/search/cs?searchtype=author&query=Pilat%2C+D">Dan Pilat</a>, <a href="/search/cs?searchtype=author&query=Pisano%2C+V">Valerie Pisano</a>, <a href="/search/cs?searchtype=author&query=Prud%27homme%2C+B">Benjamin Prud'homme</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meng Qu</a>, <a href="/search/cs?searchtype=author&query=Rahaman%2C+N">Nasim Rahaman</a>, <a href="/search/cs?searchtype=author&query=Rish%2C+I">Irina Rish</a>, <a href="/search/cs?searchtype=author&query=Rousseau%2C+J">Jean-Francois Rousseau</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+A">Abhinav Sharma</a>, <a href="/search/cs?searchtype=author&query=Struck%2C+B">Brooke Struck</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jian Tang</a>, <a href="/search/cs?searchtype=author&query=Weiss%2C+M">Martin Weiss</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+Y+W">Yun William Yu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2005.08502v2-abstract-short" style="display: inline;"> The SARS-CoV-2 (Covid-19) pandemic has caused significant strain on public health institutions around the world. Contact tracing is an essential tool to change the course of the Covid-19 pandemic. Manual contact tracing of Covid-19 cases has significant challenges that limit the ability of public health authorities to minimize community infections. Personalized peer-to-peer contact tracing through… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2005.08502v2-abstract-full').style.display = 'inline'; document.getElementById('2005.08502v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2005.08502v2-abstract-full" style="display: none;"> The SARS-CoV-2 (Covid-19) pandemic has caused significant strain on public health institutions around the world. Contact tracing is an essential tool to change the course of the Covid-19 pandemic. Manual contact tracing of Covid-19 cases has significant challenges that limit the ability of public health authorities to minimize community infections. Personalized peer-to-peer contact tracing through the use of mobile apps has the potential to shift the paradigm. Some countries have deployed centralized tracking systems, but more privacy-protecting decentralized systems offer much of the same benefit without concentrating data in the hands of a state authority or for-profit corporations. Machine learning methods can circumvent some of the limitations of standard digital tracing by incorporating many clues and their uncertainty into a more graded and precise estimation of infection risk. The estimated risk can provide early risk awareness, personalized recommendations and relevant information to the user. Finally, non-identifying risk data can inform epidemiological models trained jointly with the machine learning predictor. These models can provide statistical evidence for the importance of factors involved in disease transmission. They can also be used to monitor, evaluate and optimize health policy and (de)confinement scenarios according to medical and economic productivity indicators. However, such a strategy based on mobile apps and machine learning should proactively mitigate potential ethical and privacy risks, which could have substantial impacts on society (not only impacts on health but also impacts such as stigmatization and abuse of personal data). Here, we present an overview of the rationale, design, ethical considerations and privacy strategy of `COVI,' a Covid-19 public peer-to-peer contact tracing and risk awareness mobile application developed in Canada. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2005.08502v2-abstract-full').style.display = 'none'; document.getElementById('2005.08502v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 July, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 18 May, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2020. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">64 pages, 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/1912.00967">arXiv:1912.00967</a> <span> [<a href="https://arxiv.org/pdf/1912.00967">pdf</a>, <a href="https://arxiv.org/format/1912.00967">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Continuous Graph Neural Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xhonneux%2C+L+A+C">Louis-Pascal A. C. Xhonneux</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meng Qu</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jian Tang</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="1912.00967v3-abstract-short" style="display: inline;"> This paper builds on the connection between graph neural networks and traditional dynamical systems. We propose continuous graph neural networks (CGNN), which generalise existing graph neural networks with discrete dynamics in that they can be viewed as a specific discretisation scheme. The key idea is how to characterise the continuous dynamics of node representations, i.e. the derivatives of nod… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1912.00967v3-abstract-full').style.display = 'inline'; document.getElementById('1912.00967v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1912.00967v3-abstract-full" style="display: none;"> This paper builds on the connection between graph neural networks and traditional dynamical systems. We propose continuous graph neural networks (CGNN), which generalise existing graph neural networks with discrete dynamics in that they can be viewed as a specific discretisation scheme. The key idea is how to characterise the continuous dynamics of node representations, i.e. the derivatives of node representations, w.r.t. time. Inspired by existing diffusion-based methods on graphs (e.g. PageRank and epidemic models on social networks), we define the derivatives as a combination of the current node representations, the representations of neighbors, and the initial values of the nodes. We propose and analyse two possible dynamics on graphs---including each dimension of node representations (a.k.a. the feature channel) change independently or interact with each other---both with theoretical justification. The proposed continuous graph neural networks are robust to over-smoothing and hence allow us to build deeper networks, which in turn are able to capture the long-range dependencies between nodes. Experimental results on the task of node classification demonstrate the effectiveness of our proposed approach over competitive baselines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1912.00967v3-abstract-full').style.display = 'none'; document.getElementById('1912.00967v3-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 July, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 2 December, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1909.11715">arXiv:1909.11715</a> <span> [<a href="https://arxiv.org/pdf/1909.11715">pdf</a>, <a href="https://arxiv.org/format/1909.11715">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> GraphMix: Improved Training of GNNs for Semi-Supervised Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Verma%2C+V">Vikas Verma</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meng Qu</a>, <a href="/search/cs?searchtype=author&query=Kawaguchi%2C+K">Kenji Kawaguchi</a>, <a href="/search/cs?searchtype=author&query=Lamb%2C+A">Alex Lamb</a>, <a href="/search/cs?searchtype=author&query=Bengio%2C+Y">Yoshua Bengio</a>, <a href="/search/cs?searchtype=author&query=Kannala%2C+J">Juho Kannala</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jian Tang</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="1909.11715v3-abstract-short" style="display: inline;"> We present GraphMix, a regularization method for Graph Neural Network based semi-supervised object classification, whereby we propose to train a fully-connected network jointly with the graph neural network via parameter sharing and interpolation-based regularization. Further, we provide a theoretical analysis of how GraphMix improves the generalization bounds of the underlying graph neural networ… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1909.11715v3-abstract-full').style.display = 'inline'; document.getElementById('1909.11715v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1909.11715v3-abstract-full" style="display: none;"> We present GraphMix, a regularization method for Graph Neural Network based semi-supervised object classification, whereby we propose to train a fully-connected network jointly with the graph neural network via parameter sharing and interpolation-based regularization. Further, we provide a theoretical analysis of how GraphMix improves the generalization bounds of the underlying graph neural network, without making any assumptions about the "aggregation" layer or the depth of the graph neural networks. We experimentally validate this analysis by applying GraphMix to various architectures such as Graph Convolutional Networks, Graph Attention Networks and Graph-U-Net. Despite its simplicity, we demonstrate that GraphMix can consistently improve or closely match state-of-the-art performance using even simpler architectures such as Graph Convolutional Networks, across three established graph benchmarks: Cora, Citeseer and Pubmed citation network datasets, as well as three newly proposed datasets: Cora-Full, Co-author-CS and Co-author-Physics. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1909.11715v3-abstract-full').style.display = 'none'; document.getElementById('1909.11715v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 October, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 25 September, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">https://github.com/vikasverma1077/GraphMix</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1909.00230">arXiv:1909.00230</a> <span> [<a href="https://arxiv.org/pdf/1909.00230">pdf</a>, <a href="https://arxiv.org/format/1909.00230">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Collaborative Policy Learning for Open Knowledge Graph Reasoning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fu%2C+C">Cong Fu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+T">Tong Chen</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meng Qu</a>, <a href="/search/cs?searchtype=author&query=Jin%2C+W">Woojeong Jin</a>, <a href="/search/cs?searchtype=author&query=Ren%2C+X">Xiang Ren</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="1909.00230v1-abstract-short" style="display: inline;"> In recent years, there has been a surge of interests in interpretable graph reasoning methods. However, these models often suffer from limited performance when working on sparse and incomplete graphs, due to the lack of evidential paths that can reach target entities. Here we study open knowledge graph reasoning---a task that aims to reason for missing facts over a graph augmented by a background… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1909.00230v1-abstract-full').style.display = 'inline'; document.getElementById('1909.00230v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1909.00230v1-abstract-full" style="display: none;"> In recent years, there has been a surge of interests in interpretable graph reasoning methods. However, these models often suffer from limited performance when working on sparse and incomplete graphs, due to the lack of evidential paths that can reach target entities. Here we study open knowledge graph reasoning---a task that aims to reason for missing facts over a graph augmented by a background text corpus. A key challenge of the task is to filter out "irrelevant" facts extracted from corpus, in order to maintain an effective search space during path inference. We propose a novel reinforcement learning framework to train two collaborative agents jointly, i.e., a multi-hop graph reasoner and a fact extractor. The fact extraction agent generates fact triples from corpora to enrich the graph on the fly; while the reasoning agent provides feedback to the fact extractor and guides it towards promoting facts that are helpful for the interpretable reasoning. Experiments on two public datasets demonstrate the effectiveness of the proposed approach. Source code and datasets used in this paper can be downloaded at https://github.com/shanzhenren/CPL <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1909.00230v1-abstract-full').style.display = 'none'; document.getElementById('1909.00230v1-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 August, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1907.03179">arXiv:1907.03179</a> <span> [<a href="https://arxiv.org/pdf/1907.03179">pdf</a>, <a href="https://arxiv.org/format/1907.03179">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="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Weakly-supervised Knowledge Graph Alignment with Adversarial Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meng Qu</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jian Tang</a>, <a href="/search/cs?searchtype=author&query=Bengio%2C+Y">Yoshua Bengio</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="1907.03179v1-abstract-short" style="display: inline;"> This paper studies aligning knowledge graphs from different sources or languages. Most existing methods train supervised methods for the alignment, which usually require a large number of aligned knowledge triplets. However, such a large number of aligned knowledge triplets may not be available or are expensive to obtain in many domains. Therefore, in this paper we propose to study aligning knowle… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1907.03179v1-abstract-full').style.display = 'inline'; document.getElementById('1907.03179v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1907.03179v1-abstract-full" style="display: none;"> This paper studies aligning knowledge graphs from different sources or languages. Most existing methods train supervised methods for the alignment, which usually require a large number of aligned knowledge triplets. However, such a large number of aligned knowledge triplets may not be available or are expensive to obtain in many domains. Therefore, in this paper we propose to study aligning knowledge graphs in fully-unsupervised or weakly-supervised fashion, i.e., without or with only a few aligned triplets. We propose an unsupervised framework to align the entity and relation embddings of different knowledge graphs with an adversarial learning framework. Moreover, a regularization term which maximizes the mutual information between the embeddings of different knowledge graphs is used to mitigate the problem of mode collapse when learning the alignment functions. Such a framework can be further seamlessly integrated with existing supervised methods by utilizing a limited number of aligned triples as guidance. Experimental results on multiple datasets prove the effectiveness of our proposed approach in both the unsupervised and the weakly-supervised settings. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1907.03179v1-abstract-full').style.display = 'none'; document.getElementById('1907.03179v1-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 July, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1906.08495">arXiv:1906.08495</a> <span> [<a href="https://arxiv.org/pdf/1906.08495">pdf</a>, <a href="https://arxiv.org/format/1906.08495">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="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Probabilistic Logic Neural Networks for Reasoning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meng Qu</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jian Tang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1906.08495v2-abstract-short" style="display: inline;"> Knowledge graph reasoning, which aims at predicting the missing facts through reasoning with the observed facts, is critical to many applications. Such a problem has been widely explored by traditional logic rule-based approaches and recent knowledge graph embedding methods. A principled logic rule-based approach is the Markov Logic Network (MLN), which is able to leverage domain knowledge with fi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1906.08495v2-abstract-full').style.display = 'inline'; document.getElementById('1906.08495v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1906.08495v2-abstract-full" style="display: none;"> Knowledge graph reasoning, which aims at predicting the missing facts through reasoning with the observed facts, is critical to many applications. Such a problem has been widely explored by traditional logic rule-based approaches and recent knowledge graph embedding methods. A principled logic rule-based approach is the Markov Logic Network (MLN), which is able to leverage domain knowledge with first-order logic and meanwhile handle their uncertainty. However, the inference of MLNs is usually very difficult due to the complicated graph structures. Different from MLNs, knowledge graph embedding methods (e.g. TransE, DistMult) learn effective entity and relation embeddings for reasoning, which are much more effective and efficient. However, they are unable to leverage domain knowledge. In this paper, we propose the probabilistic Logic Neural Network (pLogicNet), which combines the advantages of both methods. A pLogicNet defines the joint distribution of all possible triplets by using a Markov logic network with first-order logic, which can be efficiently optimized with the variational EM algorithm. In the E-step, a knowledge graph embedding model is used for inferring the missing triplets, while in the M-step, the weights of logic rules are updated based on both the observed and predicted triplets. Experiments on multiple knowledge graphs prove the effectiveness of pLogicNet over many competitive baselines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1906.08495v2-abstract-full').style.display = 'none'; document.getElementById('1906.08495v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 October, 2019; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 June, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">NeurIPS 2019</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1906.07159">arXiv:1906.07159</a> <span> [<a href="https://arxiv.org/pdf/1906.07159">pdf</a>, <a href="https://arxiv.org/format/1906.07159">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> vGraph: A Generative Model for Joint Community Detection and Node Representation Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sun%2C+F">Fan-Yun Sun</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meng Qu</a>, <a href="/search/cs?searchtype=author&query=Hoffmann%2C+J">Jordan Hoffmann</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+C">Chin-Wei Huang</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jian Tang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1906.07159v2-abstract-short" style="display: inline;"> This paper focuses on two fundamental tasks of graph analysis: community detection and node representation learning, which capture the global and local structures of graphs, respectively. In the current literature, these two tasks are usually independently studied while they are actually highly correlated. We propose a probabilistic generative model called vGraph to learn community membership and… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1906.07159v2-abstract-full').style.display = 'inline'; document.getElementById('1906.07159v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1906.07159v2-abstract-full" style="display: none;"> This paper focuses on two fundamental tasks of graph analysis: community detection and node representation learning, which capture the global and local structures of graphs, respectively. In the current literature, these two tasks are usually independently studied while they are actually highly correlated. We propose a probabilistic generative model called vGraph to learn community membership and node representation collaboratively. Specifically, we assume that each node can be represented as a mixture of communities, and each community is defined as a multinomial distribution over nodes. Both the mixing coefficients and the community distribution are parameterized by the low-dimensional representations of the nodes and communities. We designed an effective variational inference algorithm which regularizes the community membership of neighboring nodes to be similar in the latent space. Experimental results on multiple real-world graphs show that vGraph is very effective in both community detection and node representation learning, outperforming many competitive baselines in both tasks. We show that the framework of vGraph is quite flexible and can be easily extended to detect hierarchical communities. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1906.07159v2-abstract-full').style.display = 'none'; document.getElementById('1906.07159v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 September, 2019; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 18 June, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted Paper at NeurIPS 2019</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1905.06214">arXiv:1905.06214</a> <span> [<a href="https://arxiv.org/pdf/1905.06214">pdf</a>, <a href="https://arxiv.org/format/1905.06214">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> GMNN: Graph Markov Neural Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meng Qu</a>, <a href="/search/cs?searchtype=author&query=Bengio%2C+Y">Yoshua Bengio</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jian Tang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1905.06214v3-abstract-short" style="display: inline;"> This paper studies semi-supervised object classification in relational data, which is a fundamental problem in relational data modeling. The problem has been extensively studied in the literature of both statistical relational learning (e.g. relational Markov networks) and graph neural networks (e.g. graph convolutional networks). Statistical relational learning methods can effectively model the d… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1905.06214v3-abstract-full').style.display = 'inline'; document.getElementById('1905.06214v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1905.06214v3-abstract-full" style="display: none;"> This paper studies semi-supervised object classification in relational data, which is a fundamental problem in relational data modeling. The problem has been extensively studied in the literature of both statistical relational learning (e.g. relational Markov networks) and graph neural networks (e.g. graph convolutional networks). Statistical relational learning methods can effectively model the dependency of object labels through conditional random fields for collective classification, whereas graph neural networks learn effective object representations for classification through end-to-end training. In this paper, we propose the Graph Markov Neural Network (GMNN) that combines the advantages of both worlds. A GMNN models the joint distribution of object labels with a conditional random field, which can be effectively trained with the variational EM algorithm. In the E-step, one graph neural network learns effective object representations for approximating the posterior distributions of object labels. In the M-step, another graph neural network is used to model the local label dependency. Experiments on object classification, link classification, and unsupervised node representation learning show that GMNN achieves state-of-the-art results. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1905.06214v3-abstract-full').style.display = 'none'; document.getElementById('1905.06214v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 July, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 May, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">icml 2019</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1904.05530">arXiv:1904.05530</a> <span> [<a href="https://arxiv.org/pdf/1904.05530">pdf</a>, <a href="https://arxiv.org/format/1904.05530">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="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Recurrent Event Network: Autoregressive Structure Inference over Temporal Knowledge Graphs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jin%2C+W">Woojeong Jin</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meng Qu</a>, <a href="/search/cs?searchtype=author&query=Jin%2C+X">Xisen Jin</a>, <a href="/search/cs?searchtype=author&query=Ren%2C+X">Xiang Ren</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1904.05530v4-abstract-short" style="display: inline;"> Knowledge graph reasoning is a critical task in natural language processing. The task becomes more challenging on temporal knowledge graphs, where each fact is associated with a timestamp. Most existing methods focus on reasoning at past timestamps and they are not able to predict facts happening in the future. This paper proposes Recurrent Event Network (RE-NET), a novel autoregressive architectu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1904.05530v4-abstract-full').style.display = 'inline'; document.getElementById('1904.05530v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1904.05530v4-abstract-full" style="display: none;"> Knowledge graph reasoning is a critical task in natural language processing. The task becomes more challenging on temporal knowledge graphs, where each fact is associated with a timestamp. Most existing methods focus on reasoning at past timestamps and they are not able to predict facts happening in the future. This paper proposes Recurrent Event Network (RE-NET), a novel autoregressive architecture for predicting future interactions. The occurrence of a fact (event) is modeled as a probability distribution conditioned on temporal sequences of past knowledge graphs. Specifically, our RE-NET employs a recurrent event encoder to encode past facts and uses a neighborhood aggregator to model the connection of facts at the same timestamp. Future facts can then be inferred in a sequential manner based on the two modules. We evaluate our proposed method via link prediction at future times on five public datasets. Through extensive experiments, we demonstrate the strength of RENET, especially on multi-step inference over future timestamps, and achieve state-of-the-art performance on all five datasets. Code and data can be found at https://github.com/INK-USC/RE-Net. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1904.05530v4-abstract-full').style.display = 'none'; document.getElementById('1904.05530v4-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 October, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 11 April, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">15 pages, 8 figures, accepted at as full paper in EMNLP 2020</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1903.00757">arXiv:1903.00757</a> <span> [<a href="https://arxiv.org/pdf/1903.00757">pdf</a>, <a href="https://arxiv.org/format/1903.00757">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1145/3308558.3313508">10.1145/3308558.3313508 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> GraphVite: A High-Performance CPU-GPU Hybrid System for Node Embedding </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhu%2C+Z">Zhaocheng Zhu</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+S">Shizhen Xu</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meng Qu</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jian Tang</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="1903.00757v1-abstract-short" style="display: inline;"> Learning continuous representations of nodes is attracting growing interest in both academia and industry recently, due to their simplicity and effectiveness in a variety of applications. Most of existing node embedding algorithms and systems are capable of processing networks with hundreds of thousands or a few millions of nodes. However, how to scale them to networks that have tens of millions o… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1903.00757v1-abstract-full').style.display = 'inline'; document.getElementById('1903.00757v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1903.00757v1-abstract-full" style="display: none;"> Learning continuous representations of nodes is attracting growing interest in both academia and industry recently, due to their simplicity and effectiveness in a variety of applications. Most of existing node embedding algorithms and systems are capable of processing networks with hundreds of thousands or a few millions of nodes. However, how to scale them to networks that have tens of millions or even hundreds of millions of nodes remains a challenging problem. In this paper, we propose GraphVite, a high-performance CPU-GPU hybrid system for training node embeddings, by co-optimizing the algorithm and the system. On the CPU end, augmented edge samples are parallelly generated by random walks in an online fashion on the network, and serve as the training data. On the GPU end, a novel parallel negative sampling is proposed to leverage multiple GPUs to train node embeddings simultaneously, without much data transfer and synchronization. Moreover, an efficient collaboration strategy is proposed to further reduce the synchronization cost between CPUs and GPUs. Experiments on multiple real-world networks show that GraphVite is super efficient. It takes only about one minute for a network with 1 million nodes and 5 million edges on a single machine with 4 GPUs, and takes around 20 hours for a network with 66 million nodes and 1.8 billion edges. Compared to the current fastest system, GraphVite is about 50 times faster without any sacrifice on performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1903.00757v1-abstract-full').style.display = 'none'; document.getElementById('1903.00757v1-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 March, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">accepted at WWW 2019</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1902.07814">arXiv:1902.07814</a> <span> [<a href="https://arxiv.org/pdf/1902.07814">pdf</a>, <a href="https://arxiv.org/format/1902.07814">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"> Learning Dual Retrieval Module for Semi-supervised Relation Extraction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lin%2C+H">Hongtao Lin</a>, <a href="/search/cs?searchtype=author&query=Yan%2C+J">Jun Yan</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meng Qu</a>, <a href="/search/cs?searchtype=author&query=Ren%2C+X">Xiang Ren</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1902.07814v2-abstract-short" style="display: inline;"> Relation extraction is an important task in structuring content of text data, and becomes especially challenging when learning with weak supervision---where only a limited number of labeled sentences are given and a large number of unlabeled sentences are available. Most existing work exploits unlabeled data based on the ideas of self-training (i.e., bootstrapping a model) and multi-view learning… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1902.07814v2-abstract-full').style.display = 'inline'; document.getElementById('1902.07814v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1902.07814v2-abstract-full" style="display: none;"> Relation extraction is an important task in structuring content of text data, and becomes especially challenging when learning with weak supervision---where only a limited number of labeled sentences are given and a large number of unlabeled sentences are available. Most existing work exploits unlabeled data based on the ideas of self-training (i.e., bootstrapping a model) and multi-view learning (e.g., ensembling multiple model variants). However, these methods either suffer from the issue of semantic drift, or do not fully capture the problem characteristics of relation extraction. In this paper, we leverage a key insight that retrieving sentences expressing a relation is a dual task of predicting relation label for a given sentence---two tasks are complementary to each other and can be optimized jointly for mutual enhancement. To model this intuition, we propose DualRE, a principled framework that introduces a retrieval module which is jointly trained with the original relation prediction module. In this way, high-quality samples selected by retrieval module from unlabeled data can be used to improve prediction module, and vice versa. Experimental results\footnote{\small Code and data can be found at \url{https://github.com/INK-USC/DualRE}.} on two public datasets as well as case studies demonstrate the effectiveness of the DualRE approach. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1902.07814v2-abstract-full').style.display = 'none'; document.getElementById('1902.07814v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 February, 2019; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 February, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10 pages, 2-page references. Accepted to The Web Conference 2019</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1711.03226">arXiv:1711.03226</a> <span> [<a href="https://arxiv.org/pdf/1711.03226">pdf</a>, <a href="https://arxiv.org/format/1711.03226">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"> Weakly-supervised Relation Extraction by Pattern-enhanced Embedding Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meng Qu</a>, <a href="/search/cs?searchtype=author&query=Ren%2C+X">Xiang Ren</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yu Zhang</a>, <a href="/search/cs?searchtype=author&query=Han%2C+J">Jiawei Han</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="1711.03226v2-abstract-short" style="display: inline;"> Extracting relations from text corpora is an important task in text mining. It becomes particularly challenging when focusing on weakly-supervised relation extraction, that is, utilizing a few relation instances (i.e., a pair of entities and their relation) as seeds to extract more instances from corpora. Existing distributional approaches leverage the corpus-level co-occurrence statistics of enti… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1711.03226v2-abstract-full').style.display = 'inline'; document.getElementById('1711.03226v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1711.03226v2-abstract-full" style="display: none;"> Extracting relations from text corpora is an important task in text mining. It becomes particularly challenging when focusing on weakly-supervised relation extraction, that is, utilizing a few relation instances (i.e., a pair of entities and their relation) as seeds to extract more instances from corpora. Existing distributional approaches leverage the corpus-level co-occurrence statistics of entities to predict their relations, and require large number of labeled instances to learn effective relation classifiers. Alternatively, pattern-based approaches perform bootstrapping or apply neural networks to model the local contexts, but still rely on large number of labeled instances to build reliable models. In this paper, we study integrating the distributional and pattern-based methods in a weakly-supervised setting, such that the two types of methods can provide complementary supervision for each other to build an effective, unified model. We propose a novel co-training framework with a distributional module and a pattern module. During training, the distributional module helps the pattern module discriminate between the informative patterns and other patterns, and the pattern module generates some highly-confident instances to improve the distributional module. The whole framework can be effectively optimized by iterating between improving the pattern module and updating the distributional module. We conduct experiments on two tasks: knowledge base completion with text corpora and corpus-level relation extraction. Experimental results prove the effectiveness of our framework in the weakly-supervised setting. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1711.03226v2-abstract-full').style.display = 'none'; document.getElementById('1711.03226v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 December, 2017; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 8 November, 2017; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2017. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1709.06636">arXiv:1709.06636</a> <span> [<a href="https://arxiv.org/pdf/1709.06636">pdf</a>, <a href="https://arxiv.org/format/1709.06636">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> An Attention-based Collaboration Framework for Multi-View Network Representation Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meng Qu</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jian Tang</a>, <a href="/search/cs?searchtype=author&query=Shang%2C+J">Jingbo Shang</a>, <a href="/search/cs?searchtype=author&query=Ren%2C+X">Xiang Ren</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+M">Ming Zhang</a>, <a href="/search/cs?searchtype=author&query=Han%2C+J">Jiawei Han</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="1709.06636v1-abstract-short" style="display: inline;"> Learning distributed node representations in networks has been attracting increasing attention recently due to its effectiveness in a variety of applications. Existing approaches usually study networks with a single type of proximity between nodes, which defines a single view of a network. However, in reality there usually exists multiple types of proximities between nodes, yielding networks with… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1709.06636v1-abstract-full').style.display = 'inline'; document.getElementById('1709.06636v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1709.06636v1-abstract-full" style="display: none;"> Learning distributed node representations in networks has been attracting increasing attention recently due to its effectiveness in a variety of applications. Existing approaches usually study networks with a single type of proximity between nodes, which defines a single view of a network. However, in reality there usually exists multiple types of proximities between nodes, yielding networks with multiple views. This paper studies learning node representations for networks with multiple views, which aims to infer robust node representations across different views. We propose a multi-view representation learning approach, which promotes the collaboration of different views and lets them vote for the robust representations. During the voting process, an attention mechanism is introduced, which enables each node to focus on the most informative views. Experimental results on real-world networks show that the proposed approach outperforms existing state-of-the-art approaches for network representation learning with a single view and other competitive approaches with multiple views. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1709.06636v1-abstract-full').style.display = 'none'; document.getElementById('1709.06636v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 September, 2017; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2017. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">CIKM 2017</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1706.08186">arXiv:1706.08186</a> <span> [<a href="https://arxiv.org/pdf/1706.08186">pdf</a>, <a href="https://arxiv.org/format/1706.08186">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"> Automatic Synonym Discovery with Knowledge Bases </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meng Qu</a>, <a href="/search/cs?searchtype=author&query=Ren%2C+X">Xiang Ren</a>, <a href="/search/cs?searchtype=author&query=Han%2C+J">Jiawei Han</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="1706.08186v1-abstract-short" style="display: inline;"> Recognizing entity synonyms from text has become a crucial task in many entity-leveraging applications. However, discovering entity synonyms from domain-specific text corpora (e.g., news articles, scientific papers) is rather challenging. Current systems take an entity name string as input to find out other names that are synonymous, ignoring the fact that often times a name string can refer to mu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1706.08186v1-abstract-full').style.display = 'inline'; document.getElementById('1706.08186v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1706.08186v1-abstract-full" style="display: none;"> Recognizing entity synonyms from text has become a crucial task in many entity-leveraging applications. However, discovering entity synonyms from domain-specific text corpora (e.g., news articles, scientific papers) is rather challenging. Current systems take an entity name string as input to find out other names that are synonymous, ignoring the fact that often times a name string can refer to multiple entities (e.g., "apple" could refer to both Apple Inc and the fruit apple). Moreover, most existing methods require training data manually created by domain experts to construct supervised-learning systems. In this paper, we study the problem of automatic synonym discovery with knowledge bases, that is, identifying synonyms for knowledge base entities in a given domain-specific corpus. The manually-curated synonyms for each entity stored in a knowledge base not only form a set of name strings to disambiguate the meaning for each other, but also can serve as "distant" supervision to help determine important features for the task. We propose a novel framework, called DPE, to integrate two kinds of mutually-complementing signals for synonym discovery, i.e., distributional features based on corpus-level statistics and textual patterns based on local contexts. In particular, DPE jointly optimizes the two kinds of signals in conjunction with distant supervision, so that they can mutually enhance each other in the training stage. At the inference stage, both signals will be utilized to discover synonyms for the given entities. Experimental results prove the effectiveness of the proposed framework. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1706.08186v1-abstract-full').style.display = 'none'; document.getElementById('1706.08186v1-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 June, 2017; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2017. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1611.09878">arXiv:1611.09878</a> <span> [<a href="https://arxiv.org/pdf/1611.09878">pdf</a>, <a href="https://arxiv.org/format/1611.09878">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Identity-sensitive Word Embedding through Heterogeneous Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jian Tang</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meng Qu</a>, <a href="/search/cs?searchtype=author&query=Mei%2C+Q">Qiaozhu Mei</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="1611.09878v1-abstract-short" style="display: inline;"> Most existing word embedding approaches do not distinguish the same words in different contexts, therefore ignoring their contextual meanings. As a result, the learned embeddings of these words are usually a mixture of multiple meanings. In this paper, we acknowledge multiple identities of the same word in different contexts and learn the \textbf{identity-sensitive} word embeddings. Based on an id… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1611.09878v1-abstract-full').style.display = 'inline'; document.getElementById('1611.09878v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1611.09878v1-abstract-full" style="display: none;"> Most existing word embedding approaches do not distinguish the same words in different contexts, therefore ignoring their contextual meanings. As a result, the learned embeddings of these words are usually a mixture of multiple meanings. In this paper, we acknowledge multiple identities of the same word in different contexts and learn the \textbf{identity-sensitive} word embeddings. Based on an identity-labeled text corpora, a heterogeneous network of words and word identities is constructed to model different-levels of word co-occurrences. The heterogeneous network is further embedded into a low-dimensional space through a principled network embedding approach, through which we are able to obtain the embeddings of words and the embeddings of word identities. We study three different types of word identities including topics, sentiments and categories. Experimental results on real-world data sets show that the identity-sensitive word embeddings learned by our approach indeed capture different meanings of words and outperforms competitive methods on tasks including text classification and word similarity computation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1611.09878v1-abstract-full').style.display = 'none'; document.getElementById('1611.09878v1-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 November, 2016; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2016. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1610.09769">arXiv:1610.09769</a> <span> [<a href="https://arxiv.org/pdf/1610.09769">pdf</a>, <a href="https://arxiv.org/format/1610.09769">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Meta-Path Guided Embedding for Similarity Search in Large-Scale Heterogeneous Information Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shang%2C+J">Jingbo Shang</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meng Qu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jialu Liu</a>, <a href="/search/cs?searchtype=author&query=Kaplan%2C+L+M">Lance M. Kaplan</a>, <a href="/search/cs?searchtype=author&query=Han%2C+J">Jiawei Han</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+J">Jian Peng</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1610.09769v1-abstract-short" style="display: inline;"> Most real-world data can be modeled as heterogeneous information networks (HINs) consisting of vertices of multiple types and their relationships. Search for similar vertices of the same type in large HINs, such as bibliographic networks and business-review networks, is a fundamental problem with broad applications. Although similarity search in HINs has been studied previously, most existing appr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1610.09769v1-abstract-full').style.display = 'inline'; document.getElementById('1610.09769v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1610.09769v1-abstract-full" style="display: none;"> Most real-world data can be modeled as heterogeneous information networks (HINs) consisting of vertices of multiple types and their relationships. Search for similar vertices of the same type in large HINs, such as bibliographic networks and business-review networks, is a fundamental problem with broad applications. Although similarity search in HINs has been studied previously, most existing approaches neither explore rich semantic information embedded in the network structures nor take user's preference as a guidance. In this paper, we re-examine similarity search in HINs and propose a novel embedding-based framework. It models vertices as low-dimensional vectors to explore network structure-embedded similarity. To accommodate user preferences at defining similarity semantics, our proposed framework, ESim, accepts user-defined meta-paths as guidance to learn vertex vectors in a user-preferred embedding space. Moreover, an efficient and parallel sampling-based optimization algorithm has been developed to learn embeddings in large-scale HINs. Extensive experiments on real-world large-scale HINs demonstrate a significant improvement on the effectiveness of ESim over several state-of-the-art algorithms as well as its scalability. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1610.09769v1-abstract-full').style.display = 'none'; document.getElementById('1610.09769v1-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 October, 2016; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2016. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1610.08763">arXiv:1610.08763</a> <span> [<a href="https://arxiv.org/pdf/1610.08763">pdf</a>, <a href="https://arxiv.org/format/1610.08763">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"> CoType: Joint Extraction of Typed Entities and Relations with Knowledge Bases </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ren%2C+X">Xiang Ren</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Z">Zeqiu Wu</a>, <a href="/search/cs?searchtype=author&query=He%2C+W">Wenqi He</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meng Qu</a>, <a href="/search/cs?searchtype=author&query=Voss%2C+C+R">Clare R. Voss</a>, <a href="/search/cs?searchtype=author&query=Ji%2C+H">Heng Ji</a>, <a href="/search/cs?searchtype=author&query=Abdelzaher%2C+T+F">Tarek F. Abdelzaher</a>, <a href="/search/cs?searchtype=author&query=Han%2C+J">Jiawei Han</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="1610.08763v2-abstract-short" style="display: inline;"> Extracting entities and relations for types of interest from text is important for understanding massive text corpora. Traditionally, systems of entity relation extraction have relied on human-annotated corpora for training and adopted an incremental pipeline. Such systems require additional human expertise to be ported to a new domain, and are vulnerable to errors cascading down the pipeline. In… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1610.08763v2-abstract-full').style.display = 'inline'; document.getElementById('1610.08763v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1610.08763v2-abstract-full" style="display: none;"> Extracting entities and relations for types of interest from text is important for understanding massive text corpora. Traditionally, systems of entity relation extraction have relied on human-annotated corpora for training and adopted an incremental pipeline. Such systems require additional human expertise to be ported to a new domain, and are vulnerable to errors cascading down the pipeline. In this paper, we investigate joint extraction of typed entities and relations with labeled data heuristically obtained from knowledge bases (i.e., distant supervision). As our algorithm for type labeling via distant supervision is context-agnostic, noisy training data poses unique challenges for the task. We propose a novel domain-independent framework, called CoType, that runs a data-driven text segmentation algorithm to extract entity mentions, and jointly embeds entity mentions, relation mentions, text features and type labels into two low-dimensional spaces (for entity and relation mentions respectively), where, in each space, objects whose types are close will also have similar representations. CoType, then using these learned embeddings, estimates the types of test (unlinkable) mentions. We formulate a joint optimization problem to learn embeddings from text corpora and knowledge bases, adopting a novel partial-label loss function for noisy labeled data and introducing an object "translation" function to capture the cross-constraints of entities and relations on each other. Experiments on three public datasets demonstrate the effectiveness of CoType across different domains (e.g., news, biomedical), with an average of 25% improvement in F1 score compared to the next best method. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1610.08763v2-abstract-full').style.display = 'none'; document.getElementById('1610.08763v2-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 June, 2017; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 27 October, 2016; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2016. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">WWW 2017</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1602.05307">arXiv:1602.05307</a> <span> [<a href="https://arxiv.org/pdf/1602.05307">pdf</a>, <a href="https://arxiv.org/format/1602.05307">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"> Label Noise Reduction in Entity Typing by Heterogeneous Partial-Label Embedding </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ren%2C+X">Xiang Ren</a>, <a href="/search/cs?searchtype=author&query=He%2C+W">Wenqi He</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meng Qu</a>, <a href="/search/cs?searchtype=author&query=Voss%2C+C+R">Clare R. Voss</a>, <a href="/search/cs?searchtype=author&query=Ji%2C+H">Heng Ji</a>, <a href="/search/cs?searchtype=author&query=Han%2C+J">Jiawei Han</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="1602.05307v1-abstract-short" style="display: inline;"> Current systems of fine-grained entity typing use distant supervision in conjunction with existing knowledge bases to assign categories (type labels) to entity mentions. However, the type labels so obtained from knowledge bases are often noisy (i.e., incorrect for the entity mention's local context). We define a new task, Label Noise Reduction in Entity Typing (LNR), to be the automatic identifica… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1602.05307v1-abstract-full').style.display = 'inline'; document.getElementById('1602.05307v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1602.05307v1-abstract-full" style="display: none;"> Current systems of fine-grained entity typing use distant supervision in conjunction with existing knowledge bases to assign categories (type labels) to entity mentions. However, the type labels so obtained from knowledge bases are often noisy (i.e., incorrect for the entity mention's local context). We define a new task, Label Noise Reduction in Entity Typing (LNR), to be the automatic identification of correct type labels (type-paths) for training examples, given the set of candidate type labels obtained by distant supervision with a given type hierarchy. The unknown type labels for individual entity mentions and the semantic similarity between entity types pose unique challenges for solving the LNR task. We propose a general framework, called PLE, to jointly embed entity mentions, text features and entity types into the same low-dimensional space where, in that space, objects whose types are semantically close have similar representations. Then we estimate the type-path for each training example in a top-down manner using the learned embeddings. We formulate a global objective for learning the embeddings from text corpora and knowledge bases, which adopts a novel margin-based loss that is robust to noisy labels and faithfully models type correlation derived from knowledge bases. Our experiments on three public typing datasets demonstrate the effectiveness and robustness of PLE, with an average of 25% improvement in accuracy compared to next best method. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1602.05307v1-abstract-full').style.display = 'none'; document.getElementById('1602.05307v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 February, 2016; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2016. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Submitted to KDD 2016. 11 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/1508.00200">arXiv:1508.00200</a> <span> [<a href="https://arxiv.org/pdf/1508.00200">pdf</a>, <a href="https://arxiv.org/format/1508.00200">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Neural and Evolutionary Computing">cs.NE</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1145/2783258.2783307">10.1145/2783258.2783307 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> PTE: Predictive Text Embedding through Large-scale Heterogeneous Text Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jian Tang</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meng Qu</a>, <a href="/search/cs?searchtype=author&query=Mei%2C+Q">Qiaozhu Mei</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="1508.00200v1-abstract-short" style="display: inline;"> Unsupervised text embedding methods, such as Skip-gram and Paragraph Vector, have been attracting increasing attention due to their simplicity, scalability, and effectiveness. However, comparing to sophisticated deep learning architectures such as convolutional neural networks, these methods usually yield inferior results when applied to particular machine learning tasks. One possible reason is th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1508.00200v1-abstract-full').style.display = 'inline'; document.getElementById('1508.00200v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1508.00200v1-abstract-full" style="display: none;"> Unsupervised text embedding methods, such as Skip-gram and Paragraph Vector, have been attracting increasing attention due to their simplicity, scalability, and effectiveness. However, comparing to sophisticated deep learning architectures such as convolutional neural networks, these methods usually yield inferior results when applied to particular machine learning tasks. One possible reason is that these text embedding methods learn the representation of text in a fully unsupervised way, without leveraging the labeled information available for the task. Although the low dimensional representations learned are applicable to many different tasks, they are not particularly tuned for any task. In this paper, we fill this gap by proposing a semi-supervised representation learning method for text data, which we call the \textit{predictive text embedding} (PTE). Predictive text embedding utilizes both labeled and unlabeled data to learn the embedding of text. The labeled information and different levels of word co-occurrence information are first represented as a large-scale heterogeneous text network, which is then embedded into a low dimensional space through a principled and efficient algorithm. This low dimensional embedding not only preserves the semantic closeness of words and documents, but also has a strong predictive power for the particular task. Compared to recent supervised approaches based on convolutional neural networks, predictive text embedding is comparable or more effective, much more efficient, and has fewer parameters to tune. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1508.00200v1-abstract-full').style.display = 'none'; document.getElementById('1508.00200v1-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 August, 2015; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2015. </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">KDD 2015</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.2.6 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1503.03578">arXiv:1503.03578</a> <span> [<a href="https://arxiv.org/pdf/1503.03578">pdf</a>, <a href="https://arxiv.org/format/1503.03578">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1145/2736277.2741093">10.1145/2736277.2741093 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> LINE: Large-scale Information Network Embedding </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jian Tang</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meng Qu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+M">Mingzhe Wang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+M">Ming Zhang</a>, <a href="/search/cs?searchtype=author&query=Yan%2C+J">Jun Yan</a>, <a href="/search/cs?searchtype=author&query=Mei%2C+Q">Qiaozhu Mei</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="1503.03578v1-abstract-short" style="display: inline;"> This paper studies the problem of embedding very large information networks into low-dimensional vector spaces, which is useful in many tasks such as visualization, node classification, and link prediction. Most existing graph embedding methods do not scale for real world information networks which usually contain millions of nodes. In this paper, we propose a novel network embedding method called… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1503.03578v1-abstract-full').style.display = 'inline'; document.getElementById('1503.03578v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1503.03578v1-abstract-full" style="display: none;"> This paper studies the problem of embedding very large information networks into low-dimensional vector spaces, which is useful in many tasks such as visualization, node classification, and link prediction. Most existing graph embedding methods do not scale for real world information networks which usually contain millions of nodes. In this paper, we propose a novel network embedding method called the "LINE," which is suitable for arbitrary types of information networks: undirected, directed, and/or weighted. The method optimizes a carefully designed objective function that preserves both the local and global network structures. An edge-sampling algorithm is proposed that addresses the limitation of the classical stochastic gradient descent and improves both the effectiveness and the efficiency of the inference. Empirical experiments prove the effectiveness of the LINE on a variety of real-world information networks, including language networks, social networks, and citation networks. The algorithm is very efficient, which is able to learn the embedding of a network with millions of vertices and billions of edges in a few hours on a typical single machine. The source code of the LINE is available online. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1503.03578v1-abstract-full').style.display = 'none'; document.getElementById('1503.03578v1-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 March, 2015; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2015. </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">WWW 2015</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1311.6542">arXiv:1311.6542</a> <span> [<a href="https://arxiv.org/pdf/1311.6542">pdf</a>, <a href="https://arxiv.org/ps/1311.6542">ps</a>, <a href="https://arxiv.org/format/1311.6542">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Logic in Computer Science">cs.LO</span> </div> </div> <p class="title is-5 mathjax"> Implementing program extraction from CL1-proofs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meixia Qu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+K">Ke Chen</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+D">Daming Zhu</a>, <a href="/search/cs?searchtype=author&query=Luan%2C+J">Junfeng Luan</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="1311.6542v1-abstract-short" style="display: inline;"> Computability logic (CoL) is a formal theory of interactive computation. It understands computational problems as games played by two players: a machine and its environment, uses logical formalism to describe valid principles of computability and formulas to represent computational problems. Logic CL1 is a deductive system for a fragment of CoL. The logical vocabulary contains all of the operators… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1311.6542v1-abstract-full').style.display = 'inline'; document.getElementById('1311.6542v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1311.6542v1-abstract-full" style="display: none;"> Computability logic (CoL) is a formal theory of interactive computation. It understands computational problems as games played by two players: a machine and its environment, uses logical formalism to describe valid principles of computability and formulas to represent computational problems. Logic CL1 is a deductive system for a fragment of CoL. The logical vocabulary contains all of the operators of classical logic and choice operators, the atoms represent elementary games i.e. predicates of classical logic. In this paper, we present a program that takes a CL1-proof of an arbitrary formula $F$, and extract a winning strategy for $F$ from that proof then play $F$ using that strategy. We hope this paper would provide a starting point for further work in program extraction of the CoL-based arithmetic and other CoL-based applied systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1311.6542v1-abstract-full').style.display = 'none'; document.getElementById('1311.6542v1-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, 2013; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2013. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">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/1207.1188">arXiv:1207.1188</a> <span> [<a href="https://arxiv.org/pdf/1207.1188">pdf</a>, <a href="https://arxiv.org/ps/1207.1188">ps</a>, <a href="https://arxiv.org/format/1207.1188">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Logic in Computer Science">cs.LO</span> </div> </div> <p class="title is-5 mathjax"> On the toggling-branching recurrence of Computability Logic </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Qu%2C+M">Meixia Qu</a>, <a href="/search/cs?searchtype=author&query=Luan%2C+J">Junfeng Luan</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+D">Daming Zhu</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="1207.1188v1-abstract-short" style="display: inline;"> We introduce a new, substantially simplified version of the toggling-branching recurrence operation of Computability Logic, prove its equivalence to Japaridze's old, "canonical" version, and also prove that both versions preserve the static property of their arguments. </span> <span class="abstract-full has-text-grey-dark mathjax" id="1207.1188v1-abstract-full" style="display: none;"> We introduce a new, substantially simplified version of the toggling-branching recurrence operation of Computability Logic, prove its equivalence to Japaridze's old, "canonical" version, and also prove that both versions preserve the static property of their arguments. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1207.1188v1-abstract-full').style.display = 'none'; document.getElementById('1207.1188v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 July, 2012; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2012. </p> </li> </ol> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository