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 1–36 of 36 results for author: <span class="mathjax">Karpatne, A</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=Karpatne%2C+A">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="Karpatne, A"> </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=Karpatne%2C+A&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="Karpatne, A"> <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/2410.11247">arXiv:2410.11247</a> <span> [<a href="https://arxiv.org/pdf/2410.11247">pdf</a>, <a href="https://arxiv.org/format/2410.11247">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="Mathematical Physics">math-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Geophysics">physics.geo-ph</span> </div> </div> <p class="title is-5 mathjax"> A Unified Framework for Forward and Inverse Problems in Subsurface Imaging using Latent Space Translations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gupta%2C+N">Naveen Gupta</a>, <a href="/search/cs?searchtype=author&query=Sawhney%2C+M">Medha Sawhney</a>, <a href="/search/cs?searchtype=author&query=Daw%2C+A">Arka Daw</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Youzuo Lin</a>, <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</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="2410.11247v2-abstract-short" style="display: inline;"> In subsurface imaging, learning the mapping from velocity maps to seismic waveforms (forward problem) and waveforms to velocity (inverse problem) is important for several applications. While traditional techniques for solving forward and inverse problems are computationally prohibitive, there is a growing interest in leveraging recent advances in deep learning to learn the mapping between velocity… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11247v2-abstract-full').style.display = 'inline'; document.getElementById('2410.11247v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.11247v2-abstract-full" style="display: none;"> In subsurface imaging, learning the mapping from velocity maps to seismic waveforms (forward problem) and waveforms to velocity (inverse problem) is important for several applications. While traditional techniques for solving forward and inverse problems are computationally prohibitive, there is a growing interest in leveraging recent advances in deep learning to learn the mapping between velocity maps and seismic waveform images directly from data. Despite the variety of architectures explored in previous works, several open questions still remain unanswered such as the effect of latent space sizes, the importance of manifold learning, the complexity of translation models, and the value of jointly solving forward and inverse problems. We propose a unified framework to systematically characterize prior research in this area termed the Generalized Forward-Inverse (GFI) framework, building on the assumption of manifolds and latent space translations. We show that GFI encompasses previous works in deep learning for subsurface imaging, which can be viewed as specific instantiations of GFI. We also propose two new model architectures within the framework of GFI: Latent U-Net and Invertible X-Net, leveraging the power of U-Nets for domain translation and the ability of IU-Nets to simultaneously learn forward and inverse translations, respectively. We show that our proposed models achieve state-of-the-art (SOTA) performance for forward and inverse problems on a wide range of synthetic datasets, and also investigate their zero-shot effectiveness on two real-world-like datasets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11247v2-abstract-full').style.display = 'none'; document.getElementById('2410.11247v2-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.02335">arXiv:2409.02335</a> <span> [<a href="https://arxiv.org/pdf/2409.02335">pdf</a>, <a href="https://arxiv.org/format/2409.02335">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"> What Do You See in Common? Learning Hierarchical Prototypes over Tree-of-Life to Discover Evolutionary Traits </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Manogaran%2C+H+B">Harish Babu Manogaran</a>, <a href="/search/cs?searchtype=author&query=Maruf%2C+M">M. Maruf</a>, <a href="/search/cs?searchtype=author&query=Daw%2C+A">Arka Daw</a>, <a href="/search/cs?searchtype=author&query=Mehrab%2C+K+S">Kazi Sajeed Mehrab</a>, <a href="/search/cs?searchtype=author&query=Charpentier%2C+C+P">Caleb Patrick Charpentier</a>, <a href="/search/cs?searchtype=author&query=Uyeda%2C+J+C">Josef C. Uyeda</a>, <a href="/search/cs?searchtype=author&query=Dahdul%2C+W">Wasila Dahdul</a>, <a href="/search/cs?searchtype=author&query=Thompson%2C+M+J">Matthew J Thompson</a>, <a href="/search/cs?searchtype=author&query=Campolongo%2C+E+G">Elizabeth G Campolongo</a>, <a href="/search/cs?searchtype=author&query=Provost%2C+K+L">Kaiya L Provost</a>, <a href="/search/cs?searchtype=author&query=Mabee%2C+P+M">Paula M. Mabee</a>, <a href="/search/cs?searchtype=author&query=Lapp%2C+H">Hilmar Lapp</a>, <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</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="2409.02335v1-abstract-short" style="display: inline;"> A grand challenge in biology is to discover evolutionary traits - features of organisms common to a group of species with a shared ancestor in the tree of life (also referred to as phylogenetic tree). With the growing availability of image repositories in biology, there is a tremendous opportunity to discover evolutionary traits directly from images in the form of a hierarchy of prototypes. Howeve… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.02335v1-abstract-full').style.display = 'inline'; document.getElementById('2409.02335v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.02335v1-abstract-full" style="display: none;"> A grand challenge in biology is to discover evolutionary traits - features of organisms common to a group of species with a shared ancestor in the tree of life (also referred to as phylogenetic tree). With the growing availability of image repositories in biology, there is a tremendous opportunity to discover evolutionary traits directly from images in the form of a hierarchy of prototypes. However, current prototype-based methods are mostly designed to operate over a flat structure of classes and face several challenges in discovering hierarchical prototypes, including the issue of learning over-specific features at internal nodes. To overcome these challenges, we introduce the framework of Hierarchy aligned Commonality through Prototypical Networks (HComP-Net). We empirically show that HComP-Net learns prototypes that are accurate, semantically consistent, and generalizable to unseen species in comparison to baselines on birds, butterflies, and fishes datasets. The code and datasets are available at https://github.com/Imageomics/HComPNet. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.02335v1-abstract-full').style.display = 'none'; document.getElementById('2409.02335v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 September, 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">34 pages, 27 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/2408.16176">arXiv:2408.16176</a> <span> [<a href="https://arxiv.org/pdf/2408.16176">pdf</a>, <a href="https://arxiv.org/format/2408.16176">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"> VLM4Bio: A Benchmark Dataset to Evaluate Pretrained Vision-Language Models for Trait Discovery from Biological Images </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Maruf%2C+M">M. Maruf</a>, <a href="/search/cs?searchtype=author&query=Daw%2C+A">Arka Daw</a>, <a href="/search/cs?searchtype=author&query=Mehrab%2C+K+S">Kazi Sajeed Mehrab</a>, <a href="/search/cs?searchtype=author&query=Manogaran%2C+H+B">Harish Babu Manogaran</a>, <a href="/search/cs?searchtype=author&query=Neog%2C+A">Abhilash Neog</a>, <a href="/search/cs?searchtype=author&query=Sawhney%2C+M">Medha Sawhney</a>, <a href="/search/cs?searchtype=author&query=Khurana%2C+M">Mridul Khurana</a>, <a href="/search/cs?searchtype=author&query=Balhoff%2C+J+P">James P. Balhoff</a>, <a href="/search/cs?searchtype=author&query=Bakis%2C+Y">Yasin Bakis</a>, <a href="/search/cs?searchtype=author&query=Altintas%2C+B">Bahadir Altintas</a>, <a href="/search/cs?searchtype=author&query=Thompson%2C+M+J">Matthew J. Thompson</a>, <a href="/search/cs?searchtype=author&query=Campolongo%2C+E+G">Elizabeth G. Campolongo</a>, <a href="/search/cs?searchtype=author&query=Uyeda%2C+J+C">Josef C. Uyeda</a>, <a href="/search/cs?searchtype=author&query=Lapp%2C+H">Hilmar Lapp</a>, <a href="/search/cs?searchtype=author&query=Bart%2C+H+L">Henry L. Bart</a>, <a href="/search/cs?searchtype=author&query=Mabee%2C+P+M">Paula M. Mabee</a>, <a href="/search/cs?searchtype=author&query=Su%2C+Y">Yu Su</a>, <a href="/search/cs?searchtype=author&query=Chao%2C+W">Wei-Lun Chao</a>, <a href="/search/cs?searchtype=author&query=Stewart%2C+C">Charles Stewart</a>, <a href="/search/cs?searchtype=author&query=Berger-Wolf%2C+T">Tanya Berger-Wolf</a>, <a href="/search/cs?searchtype=author&query=Dahdul%2C+W">Wasila Dahdul</a>, <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.16176v1-abstract-short" style="display: inline;"> Images are increasingly becoming the currency for documenting biodiversity on the planet, providing novel opportunities for accelerating scientific discoveries in the field of organismal biology, especially with the advent of large vision-language models (VLMs). We ask if pre-trained VLMs can aid scientists in answering a range of biologically relevant questions without any additional fine-tuning.… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.16176v1-abstract-full').style.display = 'inline'; document.getElementById('2408.16176v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.16176v1-abstract-full" style="display: none;"> Images are increasingly becoming the currency for documenting biodiversity on the planet, providing novel opportunities for accelerating scientific discoveries in the field of organismal biology, especially with the advent of large vision-language models (VLMs). We ask if pre-trained VLMs can aid scientists in answering a range of biologically relevant questions without any additional fine-tuning. In this paper, we evaluate the effectiveness of 12 state-of-the-art (SOTA) VLMs in the field of organismal biology using a novel dataset, VLM4Bio, consisting of 469K question-answer pairs involving 30K images from three groups of organisms: fishes, birds, and butterflies, covering five biologically relevant tasks. We also explore the effects of applying prompting techniques and tests for reasoning hallucination on the performance of VLMs, shedding new light on the capabilities of current SOTA VLMs in answering biologically relevant questions using images. The code and datasets for running all the analyses reported in this paper can be found at https://github.com/sammarfy/VLM4Bio. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.16176v1-abstract-full').style.display = 'none'; document.getElementById('2408.16176v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">36 pages, 37 figures, 7 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.00160">arXiv:2408.00160</a> <span> [<a href="https://arxiv.org/pdf/2408.00160">pdf</a>, <a href="https://arxiv.org/format/2408.00160">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Populations and Evolution">q-bio.PE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Hierarchical Conditioning of Diffusion Models Using Tree-of-Life for Studying Species Evolution </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Khurana%2C+M">Mridul Khurana</a>, <a href="/search/cs?searchtype=author&query=Daw%2C+A">Arka Daw</a>, <a href="/search/cs?searchtype=author&query=Maruf%2C+M">M. Maruf</a>, <a href="/search/cs?searchtype=author&query=Uyeda%2C+J+C">Josef C. Uyeda</a>, <a href="/search/cs?searchtype=author&query=Dahdul%2C+W">Wasila Dahdul</a>, <a href="/search/cs?searchtype=author&query=Charpentier%2C+C">Caleb Charpentier</a>, <a href="/search/cs?searchtype=author&query=Bak%C4%B1%C5%9F%2C+Y">Yasin Bak谋艧</a>, <a href="/search/cs?searchtype=author&query=Bart%2C+H+L">Henry L. Bart Jr.</a>, <a href="/search/cs?searchtype=author&query=Mabee%2C+P+M">Paula M. Mabee</a>, <a href="/search/cs?searchtype=author&query=Lapp%2C+H">Hilmar Lapp</a>, <a href="/search/cs?searchtype=author&query=Balhoff%2C+J+P">James P. Balhoff</a>, <a href="/search/cs?searchtype=author&query=Chao%2C+W">Wei-Lun Chao</a>, <a href="/search/cs?searchtype=author&query=Stewart%2C+C">Charles Stewart</a>, <a href="/search/cs?searchtype=author&query=Berger-Wolf%2C+T">Tanya Berger-Wolf</a>, <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.00160v1-abstract-short" style="display: inline;"> A central problem in biology is to understand how organisms evolve and adapt to their environment by acquiring variations in the observable characteristics or traits of species across the tree of life. With the growing availability of large-scale image repositories in biology and recent advances in generative modeling, there is an opportunity to accelerate the discovery of evolutionary traits auto… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.00160v1-abstract-full').style.display = 'inline'; document.getElementById('2408.00160v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.00160v1-abstract-full" style="display: none;"> A central problem in biology is to understand how organisms evolve and adapt to their environment by acquiring variations in the observable characteristics or traits of species across the tree of life. With the growing availability of large-scale image repositories in biology and recent advances in generative modeling, there is an opportunity to accelerate the discovery of evolutionary traits automatically from images. Toward this goal, we introduce Phylo-Diffusion, a novel framework for conditioning diffusion models with phylogenetic knowledge represented in the form of HIERarchical Embeddings (HIER-Embeds). We also propose two new experiments for perturbing the embedding space of Phylo-Diffusion: trait masking and trait swapping, inspired by counterpart experiments of gene knockout and gene editing/swapping. Our work represents a novel methodological advance in generative modeling to structure the embedding space of diffusion models using tree-based knowledge. Our work also opens a new chapter of research in evolutionary biology by using generative models to visualize evolutionary changes directly from images. We empirically demonstrate the usefulness of Phylo-Diffusion in capturing meaningful trait variations for fishes and birds, revealing novel insights about the biological mechanisms of their evolution. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.00160v1-abstract-full').style.display = 'none'; document.getElementById('2408.00160v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.08027">arXiv:2407.08027</a> <span> [<a href="https://arxiv.org/pdf/2407.08027">pdf</a>, <a href="https://arxiv.org/format/2407.08027">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"> Fish-Vista: A Multi-Purpose Dataset for Understanding & Identification of Traits from Images </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mehrab%2C+K+S">Kazi Sajeed Mehrab</a>, <a href="/search/cs?searchtype=author&query=Maruf%2C+M">M. Maruf</a>, <a href="/search/cs?searchtype=author&query=Daw%2C+A">Arka Daw</a>, <a href="/search/cs?searchtype=author&query=Manogaran%2C+H+B">Harish Babu Manogaran</a>, <a href="/search/cs?searchtype=author&query=Neog%2C+A">Abhilash Neog</a>, <a href="/search/cs?searchtype=author&query=Khurana%2C+M">Mridul Khurana</a>, <a href="/search/cs?searchtype=author&query=Altintas%2C+B">Bahadir Altintas</a>, <a href="/search/cs?searchtype=author&query=Bakis%2C+Y">Yasin Bakis</a>, <a href="/search/cs?searchtype=author&query=Campolongo%2C+E+G">Elizabeth G Campolongo</a>, <a href="/search/cs?searchtype=author&query=Thompson%2C+M+J">Matthew J Thompson</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+X">Xiaojun Wang</a>, <a href="/search/cs?searchtype=author&query=Lapp%2C+H">Hilmar Lapp</a>, <a href="/search/cs?searchtype=author&query=Chao%2C+W">Wei-Lun Chao</a>, <a href="/search/cs?searchtype=author&query=Mabee%2C+P+M">Paula M. Mabee</a>, <a href="/search/cs?searchtype=author&query=Bart%2C+H+L">Henry L. Bart Jr.</a>, <a href="/search/cs?searchtype=author&query=Dahdul%2C+W">Wasila Dahdul</a>, <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</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="2407.08027v1-abstract-short" style="display: inline;"> Fishes are integral to both ecological systems and economic sectors, and studying fish traits is crucial for understanding biodiversity patterns and macro-evolution trends. To enable the analysis of visual traits from fish images, we introduce the Fish-Visual Trait Analysis (Fish-Vista) dataset - a large, annotated collection of about 60K fish images spanning 1900 different species, supporting sev… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.08027v1-abstract-full').style.display = 'inline'; document.getElementById('2407.08027v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.08027v1-abstract-full" style="display: none;"> Fishes are integral to both ecological systems and economic sectors, and studying fish traits is crucial for understanding biodiversity patterns and macro-evolution trends. To enable the analysis of visual traits from fish images, we introduce the Fish-Visual Trait Analysis (Fish-Vista) dataset - a large, annotated collection of about 60K fish images spanning 1900 different species, supporting several challenging and biologically relevant tasks including species classification, trait identification, and trait segmentation. These images have been curated through a sophisticated data processing pipeline applied to a cumulative set of images obtained from various museum collections. Fish-Vista provides fine-grained labels of various visual traits present in each image. It also offers pixel-level annotations of 9 different traits for 2427 fish images, facilitating additional trait segmentation and localization tasks. The ultimate goal of Fish-Vista is to provide a clean, carefully curated, high-resolution dataset that can serve as a foundation for accelerating biological discoveries using advances in AI. Finally, we provide a comprehensive analysis of state-of-the-art deep learning techniques on Fish-Vista. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.08027v1-abstract-full').style.display = 'none'; document.getElementById('2407.08027v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 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/2403.15989">arXiv:2403.15989</a> <span> [<a href="https://arxiv.org/pdf/2403.15989">pdf</a>, <a href="https://arxiv.org/format/2403.15989">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="Computational Engineering, Finance, and Science">cs.CE</span> </div> </div> <p class="title is-5 mathjax"> Knowledge-guided Machine Learning: Current Trends and Future Prospects </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</a>, <a href="/search/cs?searchtype=author&query=Jia%2C+X">Xiaowei Jia</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+V">Vipin Kumar</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.15989v2-abstract-short" style="display: inline;"> This paper presents an overview of scientific modeling and discusses the complementary strengths and weaknesses of ML methods for scientific modeling in comparison to process-based models. It also provides an introduction to the current state of research in the emerging field of scientific knowledge-guided machine learning (KGML) that aims to use both scientific knowledge and data in ML frameworks… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.15989v2-abstract-full').style.display = 'inline'; document.getElementById('2403.15989v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.15989v2-abstract-full" style="display: none;"> This paper presents an overview of scientific modeling and discusses the complementary strengths and weaknesses of ML methods for scientific modeling in comparison to process-based models. It also provides an introduction to the current state of research in the emerging field of scientific knowledge-guided machine learning (KGML) that aims to use both scientific knowledge and data in ML frameworks to achieve better generalizability, scientific consistency, and explainability of results. We discuss different facets of KGML research in terms of the type of scientific knowledge used, the form of knowledge-ML integration explored, and the method for incorporating scientific knowledge in ML. We also discuss some of the common categories of use cases in environmental sciences where KGML methods are being developed, using illustrative examples in each category. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.15989v2-abstract-full').style.display = 'none'; document.getElementById('2403.15989v2-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 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 23 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2311.04157">arXiv:2311.04157</a> <span> [<a href="https://arxiv.org/pdf/2311.04157">pdf</a>, <a href="https://arxiv.org/format/2311.04157">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> A Simple Interpretable Transformer for Fine-Grained Image Classification and Analysis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Paul%2C+D">Dipanjyoti Paul</a>, <a href="/search/cs?searchtype=author&query=Chowdhury%2C+A">Arpita Chowdhury</a>, <a href="/search/cs?searchtype=author&query=Xiong%2C+X">Xinqi Xiong</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+F">Feng-Ju Chang</a>, <a href="/search/cs?searchtype=author&query=Carlyn%2C+D">David Carlyn</a>, <a href="/search/cs?searchtype=author&query=Stevens%2C+S">Samuel Stevens</a>, <a href="/search/cs?searchtype=author&query=Provost%2C+K+L">Kaiya L. Provost</a>, <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</a>, <a href="/search/cs?searchtype=author&query=Carstens%2C+B">Bryan Carstens</a>, <a href="/search/cs?searchtype=author&query=Rubenstein%2C+D">Daniel Rubenstein</a>, <a href="/search/cs?searchtype=author&query=Stewart%2C+C">Charles Stewart</a>, <a href="/search/cs?searchtype=author&query=Berger-Wolf%2C+T">Tanya Berger-Wolf</a>, <a href="/search/cs?searchtype=author&query=Su%2C+Y">Yu Su</a>, <a href="/search/cs?searchtype=author&query=Chao%2C+W">Wei-Lun Chao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2311.04157v3-abstract-short" style="display: inline;"> We present a novel usage of Transformers to make image classification interpretable. Unlike mainstream classifiers that wait until the last fully connected layer to incorporate class information to make predictions, we investigate a proactive approach, asking each class to search for itself in an image. We realize this idea via a Transformer encoder-decoder inspired by DEtection TRansformer (DETR)… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.04157v3-abstract-full').style.display = 'inline'; document.getElementById('2311.04157v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2311.04157v3-abstract-full" style="display: none;"> We present a novel usage of Transformers to make image classification interpretable. Unlike mainstream classifiers that wait until the last fully connected layer to incorporate class information to make predictions, we investigate a proactive approach, asking each class to search for itself in an image. We realize this idea via a Transformer encoder-decoder inspired by DEtection TRansformer (DETR). We learn "class-specific" queries (one for each class) as input to the decoder, enabling each class to localize its patterns in an image via cross-attention. We name our approach INterpretable TRansformer (INTR), which is fairly easy to implement and exhibits several compelling properties. We show that INTR intrinsically encourages each class to attend distinctively; the cross-attention weights thus provide a faithful interpretation of the prediction. Interestingly, via "multi-head" cross-attention, INTR could identify different "attributes" of a class, making it particularly suitable for fine-grained classification and analysis, which we demonstrate on eight datasets. Our code and pre-trained models are publicly accessible at the Imageomics Institute GitHub site: https://github.com/Imageomics/INTR. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.04157v3-abstract-full').style.display = 'none'; document.getElementById('2311.04157v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 7 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to International Conference on Learning Representations 2024 (ICLR 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/2310.09441">arXiv:2310.09441</a> <span> [<a href="https://arxiv.org/pdf/2310.09441">pdf</a>, <a href="https://arxiv.org/format/2310.09441">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="Biological Physics">physics.bio-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Quantitative Methods">q-bio.QM</span> </div> </div> <p class="title is-5 mathjax"> MEMTRACK: A Deep Learning-Based Approach to Microrobot Tracking in Dense and Low-Contrast Environments </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sawhney%2C+M">Medha Sawhney</a>, <a href="/search/cs?searchtype=author&query=Karmarkar%2C+B">Bhas Karmarkar</a>, <a href="/search/cs?searchtype=author&query=Leaman%2C+E+J">Eric J. Leaman</a>, <a href="/search/cs?searchtype=author&query=Daw%2C+A">Arka Daw</a>, <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</a>, <a href="/search/cs?searchtype=author&query=Behkam%2C+B">Bahareh Behkam</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="2310.09441v1-abstract-short" style="display: inline;"> Tracking microrobots is challenging, considering their minute size and high speed. As the field progresses towards developing microrobots for biomedical applications and conducting mechanistic studies in physiologically relevant media (e.g., collagen), this challenge is exacerbated by the dense surrounding environments with feature size and shape comparable to microrobots. Herein, we report Motion… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.09441v1-abstract-full').style.display = 'inline'; document.getElementById('2310.09441v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.09441v1-abstract-full" style="display: none;"> Tracking microrobots is challenging, considering their minute size and high speed. As the field progresses towards developing microrobots for biomedical applications and conducting mechanistic studies in physiologically relevant media (e.g., collagen), this challenge is exacerbated by the dense surrounding environments with feature size and shape comparable to microrobots. Herein, we report Motion Enhanced Multi-level Tracker (MEMTrack), a robust pipeline for detecting and tracking microrobots using synthetic motion features, deep learning-based object detection, and a modified Simple Online and Real-time Tracking (SORT) algorithm with interpolation for tracking. Our object detection approach combines different models based on the object's motion pattern. We trained and validated our model using bacterial micro-motors in collagen (tissue phantom) and tested it in collagen and aqueous media. We demonstrate that MEMTrack accurately tracks even the most challenging bacteria missed by skilled human annotators, achieving precision and recall of 77% and 48% in collagen and 94% and 35% in liquid media, respectively. Moreover, we show that MEMTrack can quantify average bacteria speed with no statistically significant difference from the laboriously-produced manual tracking data. MEMTrack represents a significant contribution to microrobot localization and tracking, and opens the potential for vision-based deep learning approaches to microrobot control in dense and low-contrast settings. All source code for training and testing MEMTrack and reproducing the results of the paper have been made publicly available https://github.com/sawhney-medha/MEMTrack. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.09441v1-abstract-full').style.display = 'none'; document.getElementById('2310.09441v1-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, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2309.14601">arXiv:2309.14601</a> <span> [<a href="https://arxiv.org/pdf/2309.14601">pdf</a>, <a href="https://arxiv.org/format/2309.14601">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="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> Neuro-Visualizer: An Auto-encoder-based Loss Landscape Visualization Method </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Elhamod%2C+M">Mohannad Elhamod</a>, <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2309.14601v1-abstract-short" style="display: inline;"> In recent years, there has been a growing interest in visualizing the loss landscape of neural networks. Linear landscape visualization methods, such as principal component analysis, have become widely used as they intuitively help researchers study neural networks and their training process. However, these linear methods suffer from limitations and drawbacks due to their lack of flexibility and l… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.14601v1-abstract-full').style.display = 'inline'; document.getElementById('2309.14601v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.14601v1-abstract-full" style="display: none;"> In recent years, there has been a growing interest in visualizing the loss landscape of neural networks. Linear landscape visualization methods, such as principal component analysis, have become widely used as they intuitively help researchers study neural networks and their training process. However, these linear methods suffer from limitations and drawbacks due to their lack of flexibility and low fidelity at representing the high dimensional landscape. In this paper, we present a novel auto-encoder-based non-linear landscape visualization method called Neuro-Visualizer that addresses these shortcoming and provides useful insights about neural network loss landscapes. To demonstrate its potential, we run experiments on a variety of problems in two separate applications of knowledge-guided machine learning (KGML). Our findings show that Neuro-Visualizer outperforms other linear and non-linear baselines and helps corroborate, and sometime challenge, claims proposed by machine learning community. All code and data used in the experiments of this paper are available at an anonymous link https://anonymous.4open.science/r/NeuroVisualizer-FDD6 <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.14601v1-abstract-full').style.display = 'none'; document.getElementById('2309.14601v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.11052">arXiv:2308.11052</a> <span> [<a href="https://arxiv.org/pdf/2308.11052">pdf</a>, <a href="https://arxiv.org/format/2308.11052">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Beyond Discriminative Regions: Saliency Maps as Alternatives to CAMs for Weakly Supervised Semantic Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Maruf%2C+M">M. Maruf</a>, <a href="/search/cs?searchtype=author&query=Daw%2C+A">Arka Daw</a>, <a href="/search/cs?searchtype=author&query=Dutta%2C+A">Amartya Dutta</a>, <a href="/search/cs?searchtype=author&query=Bu%2C+J">Jie Bu</a>, <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2308.11052v1-abstract-short" style="display: inline;"> In recent years, several Weakly Supervised Semantic Segmentation (WS3) methods have been proposed that use class activation maps (CAMs) generated by a classifier to produce pseudo-ground truths for training segmentation models. While CAMs are good at highlighting discriminative regions (DR) of an image, they are known to disregard regions of the object that do not contribute to the classifier's pr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.11052v1-abstract-full').style.display = 'inline'; document.getElementById('2308.11052v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.11052v1-abstract-full" style="display: none;"> In recent years, several Weakly Supervised Semantic Segmentation (WS3) methods have been proposed that use class activation maps (CAMs) generated by a classifier to produce pseudo-ground truths for training segmentation models. While CAMs are good at highlighting discriminative regions (DR) of an image, they are known to disregard regions of the object that do not contribute to the classifier's prediction, termed non-discriminative regions (NDR). In contrast, attribution methods such as saliency maps provide an alternative approach for assigning a score to every pixel based on its contribution to the classification prediction. This paper provides a comprehensive comparison between saliencies and CAMs for WS3. Our study includes multiple perspectives on understanding their similarities and dissimilarities. Moreover, we provide new evaluation metrics that perform a comprehensive assessment of WS3 performance of alternative methods w.r.t. CAMs. We demonstrate the effectiveness of saliencies in addressing the limitation of CAMs through our empirical studies on benchmark datasets. Furthermore, we propose random cropping as a stochastic aggregation technique that improves the performance of saliency, making it a strong alternative to CAM for WS3. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.11052v1-abstract-full').style.display = 'none'; document.getElementById('2308.11052v1-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 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">24 pages, 13 figures, 4 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.03228">arXiv:2306.03228</a> <span> [<a href="https://arxiv.org/pdf/2306.03228">pdf</a>, <a href="https://arxiv.org/format/2306.03228">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> Discovering Novel Biological Traits From Images Using Phylogeny-Guided Neural Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Elhamod%2C+M">Mohannad Elhamod</a>, <a href="/search/cs?searchtype=author&query=Khurana%2C+M">Mridul Khurana</a>, <a href="/search/cs?searchtype=author&query=Manogaran%2C+H+B">Harish Babu Manogaran</a>, <a href="/search/cs?searchtype=author&query=Uyeda%2C+J+C">Josef C. Uyeda</a>, <a href="/search/cs?searchtype=author&query=Balk%2C+M+A">Meghan A. Balk</a>, <a href="/search/cs?searchtype=author&query=Dahdul%2C+W">Wasila Dahdul</a>, <a href="/search/cs?searchtype=author&query=Bak%C4%B1%C5%9F%2C+Y">Yasin Bak谋艧</a>, <a href="/search/cs?searchtype=author&query=Bart%2C+H+L">Henry L. Bart Jr.</a>, <a href="/search/cs?searchtype=author&query=Mabee%2C+P+M">Paula M. Mabee</a>, <a href="/search/cs?searchtype=author&query=Lapp%2C+H">Hilmar Lapp</a>, <a href="/search/cs?searchtype=author&query=Balhoff%2C+J+P">James P. Balhoff</a>, <a href="/search/cs?searchtype=author&query=Charpentier%2C+C">Caleb Charpentier</a>, <a href="/search/cs?searchtype=author&query=Carlyn%2C+D">David Carlyn</a>, <a href="/search/cs?searchtype=author&query=Chao%2C+W">Wei-Lun Chao</a>, <a href="/search/cs?searchtype=author&query=Stewart%2C+C+V">Charles V. Stewart</a>, <a href="/search/cs?searchtype=author&query=Rubenstein%2C+D+I">Daniel I. Rubenstein</a>, <a href="/search/cs?searchtype=author&query=Berger-Wolf%2C+T">Tanya Berger-Wolf</a>, <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2306.03228v1-abstract-short" style="display: inline;"> Discovering evolutionary traits that are heritable across species on the tree of life (also referred to as a phylogenetic tree) is of great interest to biologists to understand how organisms diversify and evolve. However, the measurement of traits is often a subjective and labor-intensive process, making trait discovery a highly label-scarce problem. We present a novel approach for discovering evo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.03228v1-abstract-full').style.display = 'inline'; document.getElementById('2306.03228v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.03228v1-abstract-full" style="display: none;"> Discovering evolutionary traits that are heritable across species on the tree of life (also referred to as a phylogenetic tree) is of great interest to biologists to understand how organisms diversify and evolve. However, the measurement of traits is often a subjective and labor-intensive process, making trait discovery a highly label-scarce problem. We present a novel approach for discovering evolutionary traits directly from images without relying on trait labels. Our proposed approach, Phylo-NN, encodes the image of an organism into a sequence of quantized feature vectors -- or codes -- where different segments of the sequence capture evolutionary signals at varying ancestry levels in the phylogeny. We demonstrate the effectiveness of our approach in producing biologically meaningful results in a number of downstream tasks including species image generation and species-to-species image translation, using fish species as a target example. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.03228v1-abstract-full').style.display = 'none'; document.getElementById('2306.03228v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.15562">arXiv:2305.15562</a> <span> [<a href="https://arxiv.org/pdf/2305.15562">pdf</a>, <a href="https://arxiv.org/format/2305.15562">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Let There Be Order: Rethinking Ordering in Autoregressive Graph Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bu%2C+J">Jie Bu</a>, <a href="/search/cs?searchtype=author&query=Mehrab%2C+K+S">Kazi Sajeed Mehrab</a>, <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2305.15562v1-abstract-short" style="display: inline;"> Conditional graph generation tasks involve training a model to generate a graph given a set of input conditions. Many previous studies employ autoregressive models to incrementally generate graph components such as nodes and edges. However, as graphs typically lack a natural ordering among their components, converting a graph into a sequence of tokens is not straightforward. While prior works most… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.15562v1-abstract-full').style.display = 'inline'; document.getElementById('2305.15562v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.15562v1-abstract-full" style="display: none;"> Conditional graph generation tasks involve training a model to generate a graph given a set of input conditions. Many previous studies employ autoregressive models to incrementally generate graph components such as nodes and edges. However, as graphs typically lack a natural ordering among their components, converting a graph into a sequence of tokens is not straightforward. While prior works mostly rely on conventional heuristics or graph traversal methods like breadth-first search (BFS) or depth-first search (DFS) to convert graphs to sequences, the impact of ordering on graph generation has largely been unexplored. This paper contributes to this problem by: (1) highlighting the crucial role of ordering in autoregressive graph generation models, (2) proposing a novel theoretical framework that perceives ordering as a dimensionality reduction problem, thereby facilitating a deeper understanding of the relationship between orderings and generated graph accuracy, and (3) introducing "latent sort," a learning-based ordering scheme to perform dimensionality reduction of graph tokens. Our experimental results showcase the effectiveness of latent sort across a wide range of graph generation tasks, encouraging future works to further explore and develop learning-based ordering schemes for autoregressive graph generation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.15562v1-abstract-full').style.display = 'none'; document.getElementById('2305.15562v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">39 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/2211.00864">arXiv:2211.00864</a> <span> [<a href="https://arxiv.org/pdf/2211.00864">pdf</a>, <a href="https://arxiv.org/format/2211.00864">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="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Multi-task Learning for Source Attribution and Field Reconstruction for Methane Monitoring </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Daw%2C+A">Arka Daw</a>, <a href="/search/cs?searchtype=author&query=Yeo%2C+K">Kyongmin Yeo</a>, <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</a>, <a href="/search/cs?searchtype=author&query=Klein%2C+L">Levente Klein</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2211.00864v1-abstract-short" style="display: inline;"> Inferring the source information of greenhouse gases, such as methane, from spatially sparse sensor observations is an essential element in mitigating climate change. While it is well understood that the complex behavior of the atmospheric dispersion of such pollutants is governed by the Advection-Diffusion equation, it is difficult to directly apply the governing equations to identify the source… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.00864v1-abstract-full').style.display = 'inline'; document.getElementById('2211.00864v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2211.00864v1-abstract-full" style="display: none;"> Inferring the source information of greenhouse gases, such as methane, from spatially sparse sensor observations is an essential element in mitigating climate change. While it is well understood that the complex behavior of the atmospheric dispersion of such pollutants is governed by the Advection-Diffusion equation, it is difficult to directly apply the governing equations to identify the source location and magnitude (inverse problem) because of the spatially sparse and noisy observations, i.e., the pollution concentration is known only at the sensor locations and sensors sensitivity is limited. Here, we develop a multi-task learning framework that can provide high-fidelity reconstruction of the concentration field and identify emission characteristics of the pollution sources such as their location, emission strength, etc. from sparse sensor observations. We demonstrate that our proposed framework is able to achieve accurate reconstruction of the methane concentrations from sparse sensor measurements as well as precisely pin-point the location and emission strength of these pollution sources. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.00864v1-abstract-full').style.display = 'none'; document.getElementById('2211.00864v1-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 November, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 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">7 pages, 8 figures, 1 table</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2207.02338">arXiv:2207.02338</a> <span> [<a href="https://arxiv.org/pdf/2207.02338">pdf</a>, <a href="https://arxiv.org/format/2207.02338">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"> Mitigating Propagation Failures in Physics-informed Neural Networks using Retain-Resample-Release (R3) Sampling </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Daw%2C+A">Arka Daw</a>, <a href="/search/cs?searchtype=author&query=Bu%2C+J">Jie Bu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Sifan Wang</a>, <a href="/search/cs?searchtype=author&query=Perdikaris%2C+P">Paris Perdikaris</a>, <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</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="2207.02338v3-abstract-short" style="display: inline;"> Despite the success of physics-informed neural networks (PINNs) in approximating partial differential equations (PDEs), PINNs can sometimes fail to converge to the correct solution in problems involving complicated PDEs. This is reflected in several recent studies on characterizing the "failure modes" of PINNs, although a thorough understanding of the connection between PINN failure modes and samp… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.02338v3-abstract-full').style.display = 'inline'; document.getElementById('2207.02338v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2207.02338v3-abstract-full" style="display: none;"> Despite the success of physics-informed neural networks (PINNs) in approximating partial differential equations (PDEs), PINNs can sometimes fail to converge to the correct solution in problems involving complicated PDEs. This is reflected in several recent studies on characterizing the "failure modes" of PINNs, although a thorough understanding of the connection between PINN failure modes and sampling strategies is missing. In this paper, we provide a novel perspective of failure modes of PINNs by hypothesizing that training PINNs relies on successful "propagation" of solution from initial and/or boundary condition points to interior points. We show that PINNs with poor sampling strategies can get stuck at trivial solutions if there are propagation failures, characterized by highly imbalanced PDE residual fields. To mitigate propagation failures, we propose a novel Retain-Resample-Release sampling (R3) algorithm that can incrementally accumulate collocation points in regions of high PDE residuals with little to no computational overhead. We provide an extension of R3 sampling to respect the principle of causality while solving time-dependent PDEs. We theoretically analyze the behavior of R3 sampling and empirically demonstrate its efficacy and efficiency in comparison with baselines on a variety of PDE problems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.02338v3-abstract-full').style.display = 'none'; document.getElementById('2207.02338v3-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 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 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">39 pages, 53 figures, 6 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2202.05994">arXiv:2202.05994</a> <span> [<a href="https://arxiv.org/pdf/2202.05994">pdf</a>, <a href="https://arxiv.org/format/2202.05994">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="Numerical Analysis">math.NA</span> </div> </div> <p class="title is-5 mathjax"> Physics-Guided Problem Decomposition for Scaling Deep Learning of High-dimensional Eigen-Solvers: The Case of Schr枚dinger's Equation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Srivastava%2C+S">Sangeeta Srivastava</a>, <a href="/search/cs?searchtype=author&query=Olin%2C+S">Samuel Olin</a>, <a href="/search/cs?searchtype=author&query=Podolskiy%2C+V">Viktor Podolskiy</a>, <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+W">Wei-Cheng Lee</a>, <a href="/search/cs?searchtype=author&query=Arora%2C+A">Anish Arora</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="2202.05994v2-abstract-short" style="display: inline;"> Given their ability to effectively learn non-linear mappings and perform fast inference, deep neural networks (NNs) have been proposed as a viable alternative to traditional simulation-driven approaches for solving high-dimensional eigenvalue equations (HDEs), which are the foundation for many scientific applications. Unfortunately, for the learned models in these scientific applications to achiev… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2202.05994v2-abstract-full').style.display = 'inline'; document.getElementById('2202.05994v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2202.05994v2-abstract-full" style="display: none;"> Given their ability to effectively learn non-linear mappings and perform fast inference, deep neural networks (NNs) have been proposed as a viable alternative to traditional simulation-driven approaches for solving high-dimensional eigenvalue equations (HDEs), which are the foundation for many scientific applications. Unfortunately, for the learned models in these scientific applications to achieve generalization, a large, diverse, and preferably annotated dataset is typically needed and is computationally expensive to obtain. Furthermore, the learned models tend to be memory- and compute-intensive primarily due to the size of the output layer. While generalization, especially extrapolation, with scarce data has been attempted by imposing physical constraints in the form of physics loss, the problem of model scalability has remained. In this paper, we alleviate the compute bottleneck in the output layer by using physics knowledge to decompose the complex regression task of predicting the high-dimensional eigenvectors into multiple simpler sub-tasks, each of which are learned by a simple "expert" network. We call the resulting architecture of specialized experts Physics-Guided Mixture-of-Experts (PG-MoE). We demonstrate the efficacy of such physics-guided problem decomposition for the case of the Schr枚dinger's Equation in Quantum Mechanics. Our proposed PG-MoE model predicts the ground-state solution, i.e., the eigenvector that corresponds to the smallest possible eigenvalue. The model is 150x smaller than the network trained to learn the complex task while being competitive in generalization. To improve the generalization of the PG-MoE, we also employ a physics-guided loss function based on variational energy, which by quantum mechanics principles is minimized iff the output is the ground-state solution. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2202.05994v2-abstract-full').style.display = 'none'; document.getElementById('2202.05994v2-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 February, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 12 February, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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">9 pages, Submitted to SIGKDD in Feb 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/2111.08626">arXiv:2111.08626</a> <span> [<a href="https://arxiv.org/pdf/2111.08626">pdf</a>, <a href="https://arxiv.org/format/2111.08626">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="Computational Engineering, Finance, and Science">cs.CE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Numerical Analysis">math.NA</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</span> </div> </div> <p class="title is-5 mathjax"> Adjoint-Matching Neural Network Surrogates for Fast 4D-Var Data Assimilation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chennault%2C+A">Austin Chennault</a>, <a href="/search/cs?searchtype=author&query=Popov%2C+A+A">Andrey A. Popov</a>, <a href="/search/cs?searchtype=author&query=Subrahmanya%2C+A+N">Amit N. Subrahmanya</a>, <a href="/search/cs?searchtype=author&query=Cooper%2C+R">Rachel Cooper</a>, <a href="/search/cs?searchtype=author&query=Rafid%2C+A+H+M">Ali Haisam Muhammad Rafid</a>, <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</a>, <a href="/search/cs?searchtype=author&query=Sandu%2C+A">Adrian Sandu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2111.08626v2-abstract-short" style="display: inline;"> Data assimilation is the process of fusing information from imperfect computer simulations with noisy, sparse measurements of reality to obtain improved estimates of the state or parameters of a dynamical system of interest. The data assimilation procedures used in many geoscience applications, such as numerical weather forecasting, are variants of the our-dimensional variational (4D-Var) algorith… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.08626v2-abstract-full').style.display = 'inline'; document.getElementById('2111.08626v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2111.08626v2-abstract-full" style="display: none;"> Data assimilation is the process of fusing information from imperfect computer simulations with noisy, sparse measurements of reality to obtain improved estimates of the state or parameters of a dynamical system of interest. The data assimilation procedures used in many geoscience applications, such as numerical weather forecasting, are variants of the our-dimensional variational (4D-Var) algorithm. The cost of solving the underlying 4D-Var optimization problem is dominated by the cost of repeated forward and adjoint model runs. This motivates substituting the evaluations of the physical model and its adjoint by fast, approximate surrogate models. Neural networks offer a promising approach for the data-driven creation of surrogate models. The accuracy of the surrogate 4D-Var solution depends on the accuracy with each the surrogate captures both the forward and the adjoint model dynamics. We formulate and analyze several approaches to incorporate adjoint information into the construction of neural network surrogates. The resulting networks are tested on unseen data and in a sequential data assimilation problem using the Lorenz-63 system. Surrogates constructed using adjoint information demonstrate superior performance on the 4D-Var data assimilation problem compared to a standard neural network surrogate that uses only forward dynamics information. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.08626v2-abstract-full').style.display = 'none'; document.getElementById('2111.08626v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 December, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 16 November, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Report number:</span> CSL-TR-21-7 <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 34A55; 68T07; 90C30; 65L09 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2110.00684">arXiv:2110.00684</a> <span> [<a href="https://arxiv.org/pdf/2110.00684">pdf</a>, <a href="https://arxiv.org/format/2110.00684">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"> Learning Compact Representations of Neural Networks using DiscriminAtive Masking (DAM) </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bu%2C+J">Jie Bu</a>, <a href="/search/cs?searchtype=author&query=Daw%2C+A">Arka Daw</a>, <a href="/search/cs?searchtype=author&query=Maruf%2C+M">M. Maruf</a>, <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</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="2110.00684v1-abstract-short" style="display: inline;"> A central goal in deep learning is to learn compact representations of features at every layer of a neural network, which is useful for both unsupervised representation learning and structured network pruning. While there is a growing body of work in structured pruning, current state-of-the-art methods suffer from two key limitations: (i) instability during training, and (ii) need for an additiona… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2110.00684v1-abstract-full').style.display = 'inline'; document.getElementById('2110.00684v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2110.00684v1-abstract-full" style="display: none;"> A central goal in deep learning is to learn compact representations of features at every layer of a neural network, which is useful for both unsupervised representation learning and structured network pruning. While there is a growing body of work in structured pruning, current state-of-the-art methods suffer from two key limitations: (i) instability during training, and (ii) need for an additional step of fine-tuning, which is resource-intensive. At the core of these limitations is the lack of a systematic approach that jointly prunes and refines weights during training in a single stage, and does not require any fine-tuning upon convergence to achieve state-of-the-art performance. We present a novel single-stage structured pruning method termed DiscriminAtive Masking (DAM). The key intuition behind DAM is to discriminatively prefer some of the neurons to be refined during the training process, while gradually masking out other neurons. We show that our proposed DAM approach has remarkably good performance over various applications, including dimensionality reduction, recommendation system, graph representation learning, and structured pruning for image classification. We also theoretically show that the learning objective of DAM is directly related to minimizing the L0 norm of the masking layer. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2110.00684v1-abstract-full').style.display = 'none'; document.getElementById('2110.00684v1-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, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">25 pages, 11 figures, 7 tables, Accepted to NeurIPS 2021</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2106.02993">arXiv:2106.02993</a> <span> [<a href="https://arxiv.org/pdf/2106.02993">pdf</a>, <a href="https://arxiv.org/format/2106.02993">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 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/10.1145/3447548.3467449">10.1145/3447548.3467449 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> PID-GAN: A GAN Framework based on a Physics-informed Discriminator for Uncertainty Quantification with Physics </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Daw%2C+A">Arka Daw</a>, <a href="/search/cs?searchtype=author&query=Maruf%2C+M">M. Maruf</a>, <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2106.02993v1-abstract-short" style="display: inline;"> As applications of deep learning (DL) continue to seep into critical scientific use-cases, the importance of performing uncertainty quantification (UQ) with DL has become more pressing than ever before. In scientific applications, it is also important to inform the learning of DL models with knowledge of physics of the problem to produce physically consistent and generalized solutions. This is ref… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.02993v1-abstract-full').style.display = 'inline'; document.getElementById('2106.02993v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2106.02993v1-abstract-full" style="display: none;"> As applications of deep learning (DL) continue to seep into critical scientific use-cases, the importance of performing uncertainty quantification (UQ) with DL has become more pressing than ever before. In scientific applications, it is also important to inform the learning of DL models with knowledge of physics of the problem to produce physically consistent and generalized solutions. This is referred to as the emerging field of physics-informed deep learning (PIDL). We consider the problem of developing PIDL formulations that can also perform UQ. To this end, we propose a novel physics-informed GAN architecture, termed PID-GAN, where the knowledge of physics is used to inform the learning of both the generator and discriminator models, making ample use of unlabeled data instances. We show that our proposed PID-GAN framework does not suffer from imbalance of generator gradients from multiple loss terms as compared to state-of-the-art. We also empirically demonstrate the efficacy of our proposed framework on a variety of case studies involving benchmark physics-based PDEs as well as imperfect physics. All the code and datasets used in this study have been made available on this link : https://github.com/arkadaw9/PID-GAN. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.02993v1-abstract-full').style.display = 'none'; document.getElementById('2106.02993v1-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, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">11 pages, 11 figures, 2 tables, Published at KDD 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/2104.04485">arXiv:2104.04485</a> <span> [<a href="https://arxiv.org/pdf/2104.04485">pdf</a>, <a href="https://arxiv.org/format/2104.04485">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/10.1016/j.cma.2022.115126">10.1016/j.cma.2022.115126 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> A Data-Driven Approach to Full-Field Damage and Failure Pattern Prediction in Microstructure-Dependent Composites using Deep Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sepasdar%2C+R">Reza Sepasdar</a>, <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</a>, <a href="/search/cs?searchtype=author&query=Shakiba%2C+M">Maryam Shakiba</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2104.04485v1-abstract-short" style="display: inline;"> An image-based deep learning framework is developed in this paper to predict damage and failure in microstructure-dependent composite materials. The work is motivated by the complexity and computational cost of high-fidelity simulations of such materials. The proposed deep learning framework predicts the post-failure full-field stress distribution and crack pattern in two-dimensional representatio… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2104.04485v1-abstract-full').style.display = 'inline'; document.getElementById('2104.04485v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2104.04485v1-abstract-full" style="display: none;"> An image-based deep learning framework is developed in this paper to predict damage and failure in microstructure-dependent composite materials. The work is motivated by the complexity and computational cost of high-fidelity simulations of such materials. The proposed deep learning framework predicts the post-failure full-field stress distribution and crack pattern in two-dimensional representations of the composites based on the geometry of microstructures. The material of interest is selected to be a high-performance unidirectional carbon fiber-reinforced polymer composite. The deep learning framework contains two stacked fully-convolutional networks, namely, Generator 1 and Generator 2, trained sequentially. First, Generator 1 learns to translate the microstructural geometry to the full-field post-failure stress distribution. Then, Generator 2 learns to translate the output of Generator 1 to the failure pattern. A physics-informed loss function is also designed and incorporated to further improve the performance of the proposed framework and facilitate the validation process. In order to provide a sufficiently large data set for training and validating the deep learning framework, 4500 microstructural representations are synthetically generated and simulated in an efficient finite element framework. It is shown that the proposed deep learning approach can effectively predict the composites' post-failure full-field stress distribution and failure pattern, two of the most complex phenomena to simulate in computational solid mechanics. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2104.04485v1-abstract-full').style.display = 'none'; document.getElementById('2104.04485v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 April, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2101.08366">arXiv:2101.08366</a> <span> [<a href="https://arxiv.org/pdf/2101.08366">pdf</a>, <a href="https://arxiv.org/format/2101.08366">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="Computational Engineering, Finance, and Science">cs.CE</span> </div> </div> <p class="title is-5 mathjax"> Quadratic Residual Networks: A New Class of Neural Networks for Solving Forward and Inverse Problems in Physics Involving PDEs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bu%2C+J">Jie Bu</a>, <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</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="2101.08366v2-abstract-short" style="display: inline;"> We propose quadratic residual networks (QRes) as a new type of parameter-efficient neural network architecture, by adding a quadratic residual term to the weighted sum of inputs before applying activation functions. With sufficiently high functional capacity (or expressive power), we show that it is especially powerful for solving forward and inverse physics problems involving partial differential… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.08366v2-abstract-full').style.display = 'inline'; document.getElementById('2101.08366v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2101.08366v2-abstract-full" style="display: none;"> We propose quadratic residual networks (QRes) as a new type of parameter-efficient neural network architecture, by adding a quadratic residual term to the weighted sum of inputs before applying activation functions. With sufficiently high functional capacity (or expressive power), we show that it is especially powerful for solving forward and inverse physics problems involving partial differential equations (PDEs). Using tools from algebraic geometry, we theoretically demonstrate that, in contrast to plain neural networks, QRes shows better parameter efficiency in terms of network width and depth thanks to higher non-linearity in every neuron. Finally, we empirically show that QRes shows faster convergence speed in terms of number of training epochs especially in learning complex patterns. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.08366v2-abstract-full').style.display = 'none'; document.getElementById('2101.08366v2-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 January, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 January, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by SIAM International Conference on Data Mining (SDM21)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2010.00067">arXiv:2010.00067</a> <span> [<a href="https://arxiv.org/pdf/2010.00067">pdf</a>, <a href="https://arxiv.org/format/2010.00067">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"> GCNNMatch: Graph Convolutional Neural Networks for Multi-Object Tracking via Sinkhorn Normalization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Papakis%2C+I">Ioannis Papakis</a>, <a href="/search/cs?searchtype=author&query=Sarkar%2C+A">Abhijit Sarkar</a>, <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</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="2010.00067v4-abstract-short" style="display: inline;"> This paper proposes a novel method for online Multi-Object Tracking (MOT) using Graph Convolutional Neural Network (GCNN) based feature extraction and end-to-end feature matching for object association. The Graph based approach incorporates both appearance and geometry of objects at past frames as well as the current frame into the task of feature learning. This new paradigm enables the network to… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2010.00067v4-abstract-full').style.display = 'inline'; document.getElementById('2010.00067v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2010.00067v4-abstract-full" style="display: none;"> This paper proposes a novel method for online Multi-Object Tracking (MOT) using Graph Convolutional Neural Network (GCNN) based feature extraction and end-to-end feature matching for object association. The Graph based approach incorporates both appearance and geometry of objects at past frames as well as the current frame into the task of feature learning. This new paradigm enables the network to leverage the "context" information of the geometry of objects and allows us to model the interactions among the features of multiple objects. Another central innovation of our proposed framework is the use of the Sinkhorn algorithm for end-to-end learning of the associations among objects during model training. The network is trained to predict object associations by taking into account constraints specific to the MOT task. Experimental results demonstrate the efficacy of the proposed approach in achieving top performance on the MOT '15, '16, '17 and '20 Challenges among state-of-the-art online approaches. The code is available at https://github.com/IPapakis/GCNNMatch. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2010.00067v4-abstract-full').style.display = 'none'; document.getElementById('2010.00067v4-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 April, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 30 September, 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/2007.01423">arXiv:2007.01423</a> <span> [<a href="https://arxiv.org/pdf/2007.01423">pdf</a>, <a href="https://arxiv.org/format/2007.01423">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"> Maximizing Cohesion and Separation in Graph Representation Learning: A Distance-aware Negative Sampling Approach </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Maruf%2C+M">M. Maruf</a>, <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</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="2007.01423v2-abstract-short" style="display: inline;"> The objective of unsupervised graph representation learning (GRL) is to learn a low-dimensional space of node embeddings that reflect the structure of a given unlabeled graph. Existing algorithms for this task rely on negative sampling objectives that maximize the similarity in node embeddings at nearby nodes (referred to as "cohesion") by maintaining positive and negative corpus of node pairs. Wh… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2007.01423v2-abstract-full').style.display = 'inline'; document.getElementById('2007.01423v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2007.01423v2-abstract-full" style="display: none;"> The objective of unsupervised graph representation learning (GRL) is to learn a low-dimensional space of node embeddings that reflect the structure of a given unlabeled graph. Existing algorithms for this task rely on negative sampling objectives that maximize the similarity in node embeddings at nearby nodes (referred to as "cohesion") by maintaining positive and negative corpus of node pairs. While positive samples are drawn from node pairs that co-occur in short random walks, conventional approaches construct negative corpus by uniformly sampling random pairs, thus ignoring valuable information about structural dissimilarity among distant node pairs (referred to as "separation"). In this paper, we present a novel Distance-aware Negative Sampling (DNS) which maximizes the separation of distant node-pairs while maximizing cohesion at nearby node-pairs by setting the negative sampling probability proportional to the pair-wise shortest distances. Our approach can be used in conjunction with any GRL algorithm and we demonstrate the efficacy of our approach over baseline negative sampling methods over downstream node classification tasks on a number of benchmark datasets and GRL algorithms. All our codes and datasets are available at https://github.com/Distance-awareNS/DNS/. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2007.01423v2-abstract-full').style.display = 'none'; document.getElementById('2007.01423v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 January, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 2 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">14 pages, 9 figures, 3 tables, full length version with appendix; Published in Proceedings of the 2021 SIAM International Conference on Data Mining</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2007.01420">arXiv:2007.01420</a> <span> [<a href="https://arxiv.org/pdf/2007.01420">pdf</a>, <a href="https://arxiv.org/format/2007.01420">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="Computational Physics">physics.comp-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Quantum Physics">quant-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> CoPhy-PGNN: Learning Physics-guided Neural Networks with Competing Loss Functions for Solving Eigenvalue Problems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Elhamod%2C+M">Mohannad Elhamod</a>, <a href="/search/cs?searchtype=author&query=Bu%2C+J">Jie Bu</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+C">Christopher Singh</a>, <a href="/search/cs?searchtype=author&query=Redell%2C+M">Matthew Redell</a>, <a href="/search/cs?searchtype=author&query=Ghosh%2C+A">Abantika Ghosh</a>, <a href="/search/cs?searchtype=author&query=Podolskiy%2C+V">Viktor Podolskiy</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+W">Wei-Cheng Lee</a>, <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</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="2007.01420v8-abstract-short" style="display: inline;"> Physics-guided Neural Networks (PGNNs) represent an emerging class of neural networks that are trained using physics-guided (PG) loss functions (capturing violations in network outputs with known physics), along with the supervision contained in data. Existing work in PGNNs has demonstrated the efficacy of adding single PG loss functions in the neural network objectives, using constant trade-off p… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2007.01420v8-abstract-full').style.display = 'inline'; document.getElementById('2007.01420v8-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2007.01420v8-abstract-full" style="display: none;"> Physics-guided Neural Networks (PGNNs) represent an emerging class of neural networks that are trained using physics-guided (PG) loss functions (capturing violations in network outputs with known physics), along with the supervision contained in data. Existing work in PGNNs has demonstrated the efficacy of adding single PG loss functions in the neural network objectives, using constant trade-off parameters, to ensure better generalizability. However, in the presence of multiple PG functions with competing gradient directions, there is a need to adaptively tune the contribution of different PG loss functions during the course of training to arrive at generalizable solutions. We demonstrate the presence of competing PG losses in the generic neural network problem of solving for the lowest (or highest) eigenvector of a physics-based eigenvalue equation, which is commonly encountered in many scientific problems. We present a novel approach to handle competing PG losses and demonstrate its efficacy in learning generalizable solutions in two motivating applications of quantum mechanics and electromagnetic propagation. All the code and data used in this work is available at https://github.com/jayroxis/Cophy-PGNN. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2007.01420v8-abstract-full').style.display = 'none'; document.getElementById('2007.01420v8-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 December, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 2 July, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2001.11086">arXiv:2001.11086</a> <span> [<a href="https://arxiv.org/pdf/2001.11086">pdf</a>, <a href="https://arxiv.org/format/2001.11086">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="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Physics-Guided Machine Learning for Scientific Discovery: An Application in Simulating Lake Temperature Profiles </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jia%2C+X">Xiaowei Jia</a>, <a href="/search/cs?searchtype=author&query=Willard%2C+J">Jared Willard</a>, <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</a>, <a href="/search/cs?searchtype=author&query=Read%2C+J+S">Jordan S Read</a>, <a href="/search/cs?searchtype=author&query=Zwart%2C+J+A">Jacob A Zwart</a>, <a href="/search/cs?searchtype=author&query=Steinbach%2C+M">Michael Steinbach</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+V">Vipin Kumar</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2001.11086v3-abstract-short" style="display: inline;"> Physics-based models of dynamical systems are often used to study engineering and environmental systems. Despite their extensive use, these models have several well-known limitations due to simplified representations of the physical processes being modeled or challenges in selecting appropriate parameters. While-state-of-the-art machine learning models can sometimes outperform physics-based models… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2001.11086v3-abstract-full').style.display = 'inline'; document.getElementById('2001.11086v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2001.11086v3-abstract-full" style="display: none;"> Physics-based models of dynamical systems are often used to study engineering and environmental systems. Despite their extensive use, these models have several well-known limitations due to simplified representations of the physical processes being modeled or challenges in selecting appropriate parameters. While-state-of-the-art machine learning models can sometimes outperform physics-based models given ample amount of training data, they can produce results that are physically inconsistent. This paper proposes a physics-guided recurrent neural network model (PGRNN) that combines RNNs and physics-based models to leverage their complementary strengths and improves the modeling of physical processes. Specifically, we show that a PGRNN can improve prediction accuracy over that of physics-based models, while generating outputs consistent with physical laws. An important aspect of our PGRNN approach lies in its ability to incorporate the knowledge encoded in physics-based models. This allows training the PGRNN model using very few true observed data while also ensuring high prediction accuracy. Although we present and evaluate this methodology in the context of modeling the dynamics of temperature in lakes, it is applicable more widely to a range of scientific and engineering disciplines where physics-based (also known as mechanistic) models are used, e.g., climate science, materials science, computational chemistry, and biomedicine. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2001.11086v3-abstract-full').style.display = 'none'; document.getElementById('2001.11086v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 September, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 28 January, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 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">arXiv admin note: text overlap with arXiv:1810.13075</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1911.04240">arXiv:1911.04240</a> <span> [<a href="https://arxiv.org/pdf/1911.04240">pdf</a>, <a href="https://arxiv.org/format/1911.04240">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="Computational Physics">physics.comp-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Physics-guided Design and Learning of Neural Networks for Predicting Drag Force on Particle Suspensions in Moving Fluids </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Muralidhar%2C+N">Nikhil Muralidhar</a>, <a href="/search/cs?searchtype=author&query=Bu%2C+J">Jie Bu</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+Z">Ze Cao</a>, <a href="/search/cs?searchtype=author&query=He%2C+L">Long He</a>, <a href="/search/cs?searchtype=author&query=Ramakrishnan%2C+N">Naren Ramakrishnan</a>, <a href="/search/cs?searchtype=author&query=Tafti%2C+D">Danesh Tafti</a>, <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1911.04240v1-abstract-short" style="display: inline;"> Physics-based simulations are often used to model and understand complex physical systems and processes in domains like fluid dynamics. Such simulations, although used frequently, have many limitations which could arise either due to the inability to accurately model a physical process owing to incomplete knowledge about certain facets of the process or due to the underlying process being too comp… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1911.04240v1-abstract-full').style.display = 'inline'; document.getElementById('1911.04240v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1911.04240v1-abstract-full" style="display: none;"> Physics-based simulations are often used to model and understand complex physical systems and processes in domains like fluid dynamics. Such simulations, although used frequently, have many limitations which could arise either due to the inability to accurately model a physical process owing to incomplete knowledge about certain facets of the process or due to the underlying process being too complex to accurately encode into a simulation model. In such situations, it is often useful to rely on machine learning methods to fill in the gap by learning a model of the complex physical process directly from simulation data. However, as data generation through simulations is costly, we need to develop models, being cognizant of data paucity issues. In such scenarios it is often helpful if the rich physical knowledge of the application domain is incorporated in the architectural design of machine learning models. Further, we can also use information from physics-based simulations to guide the learning process using aggregate supervision to favorably constrain the learning process. In this paper, we propose PhyDNN, a deep learning model using physics-guided structural priors and physics-guided aggregate supervision for modeling the drag forces acting on each particle in a Computational Fluid Dynamics-Discrete Element Method(CFD-DEM). We conduct extensive experiments in the context of drag force prediction and showcase the usefulness of including physics knowledge in our deep learning formulation both in the design and through learning process. Our proposed PhyDNN model has been compared to several state-of-the-art models and achieves a significant performance improvement of 8.46% on average across all baseline models. The source code has been made available and the dataset used is detailed in [1, 2]. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1911.04240v1-abstract-full').style.display = 'none'; document.getElementById('1911.04240v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 November, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68T99; 76T20 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1911.02682">arXiv:1911.02682</a> <span> [<a href="https://arxiv.org/pdf/1911.02682">pdf</a>, <a href="https://arxiv.org/format/1911.02682">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="Computational Physics">physics.comp-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Physics-Guided Architecture (PGA) of Neural Networks for Quantifying Uncertainty in Lake Temperature Modeling </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Daw%2C+A">Arka Daw</a>, <a href="/search/cs?searchtype=author&query=Thomas%2C+R+Q">R. Quinn Thomas</a>, <a href="/search/cs?searchtype=author&query=Carey%2C+C+C">Cayelan C. Carey</a>, <a href="/search/cs?searchtype=author&query=Read%2C+J+S">Jordan S. Read</a>, <a href="/search/cs?searchtype=author&query=Appling%2C+A+P">Alison P. Appling</a>, <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1911.02682v1-abstract-short" style="display: inline;"> To simultaneously address the rising need of expressing uncertainties in deep learning models along with producing model outputs which are consistent with the known scientific knowledge, we propose a novel physics-guided architecture (PGA) of neural networks in the context of lake temperature modeling where the physical constraints are hard coded in the neural network architecture. This allows us… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1911.02682v1-abstract-full').style.display = 'inline'; document.getElementById('1911.02682v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1911.02682v1-abstract-full" style="display: none;"> To simultaneously address the rising need of expressing uncertainties in deep learning models along with producing model outputs which are consistent with the known scientific knowledge, we propose a novel physics-guided architecture (PGA) of neural networks in the context of lake temperature modeling where the physical constraints are hard coded in the neural network architecture. This allows us to integrate such models with state of the art uncertainty estimation approaches such as Monte Carlo (MC) Dropout without sacrificing the physical consistency of our results. We demonstrate the effectiveness of our approach in ensuring better generalizability as well as physical consistency in MC estimates over data collected from Lake Mendota in Wisconsin and Falling Creek Reservoir in Virginia, even with limited training data. We further show that our MC estimates correctly match the distribution of ground-truth observations, thus making the PGA paradigm amenable to physically grounded uncertainty quantification. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1911.02682v1-abstract-full').style.display = 'none'; document.getElementById('1911.02682v1-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 November, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">11 pages, 15 figures, 2 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1906.01450">arXiv:1906.01450</a> <span> [<a href="https://arxiv.org/pdf/1906.01450">pdf</a>, <a href="https://arxiv.org/ps/1906.01450">ps</a>, <a href="https://arxiv.org/format/1906.01450">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"> A Fast-Optimal Guaranteed Algorithm For Learning Sub-Interval Relationships in Time Series </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Agrawal%2C+S">Saurabh Agrawal</a>, <a href="/search/cs?searchtype=author&query=Verma%2C+S">Saurabh Verma</a>, <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</a>, <a href="/search/cs?searchtype=author&query=Liess%2C+S">Stefan Liess</a>, <a href="/search/cs?searchtype=author&query=Chatterjee%2C+S">Snigdhansu Chatterjee</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+V">Vipin Kumar</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1906.01450v1-abstract-short" style="display: inline;"> Traditional approaches focus on finding relationships between two entire time series, however, many interesting relationships exist in small sub-intervals of time and remain feeble during other sub-intervals. We define the notion of a sub-interval relationship (SIR) to capture such interactions that are prominent only in certain sub-intervals of time. To that end, we propose a fast-optimal guarant… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1906.01450v1-abstract-full').style.display = 'inline'; document.getElementById('1906.01450v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1906.01450v1-abstract-full" style="display: none;"> Traditional approaches focus on finding relationships between two entire time series, however, many interesting relationships exist in small sub-intervals of time and remain feeble during other sub-intervals. We define the notion of a sub-interval relationship (SIR) to capture such interactions that are prominent only in certain sub-intervals of time. To that end, we propose a fast-optimal guaranteed algorithm to find most interesting SIR relationship in a pair of time series. Lastly, we demonstrate the utility of our method in climate science domain based on a real-world dataset along with its scalability scope and obtain useful domain insights. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1906.01450v1-abstract-full').style.display = 'none'; document.getElementById('1906.01450v1-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, 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 at The Thirty-sixth International Conference on Machine Learning (ICML 2019), Time Series Workshop. arXiv admin note: substantial text overlap with arXiv:1802.06095</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1810.13075">arXiv:1810.13075</a> <span> [<a href="https://arxiv.org/pdf/1810.13075">pdf</a>, <a href="https://arxiv.org/format/1810.13075">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computational Physics">physics.comp-ph</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"> Physics Guided RNNs for Modeling Dynamical Systems: A Case Study in Simulating Lake Temperature Profiles </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jia%2C+X">Xiaowei Jia</a>, <a href="/search/cs?searchtype=author&query=Willard%2C+J">Jared Willard</a>, <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</a>, <a href="/search/cs?searchtype=author&query=Read%2C+J">Jordan Read</a>, <a href="/search/cs?searchtype=author&query=Zwart%2C+J">Jacob Zwart</a>, <a href="/search/cs?searchtype=author&query=Steinbach%2C+M">Michael Steinbach</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+V">Vipin Kumar</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1810.13075v2-abstract-short" style="display: inline;"> This paper proposes a physics-guided recurrent neural network model (PGRNN) that combines RNNs and physics-based models to leverage their complementary strengths and improve the modeling of physical processes. Specifically, we show that a PGRNN can improve prediction accuracy over that of physical models, while generating outputs consistent with physical laws, and achieving good generalizability.… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1810.13075v2-abstract-full').style.display = 'inline'; document.getElementById('1810.13075v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1810.13075v2-abstract-full" style="display: none;"> This paper proposes a physics-guided recurrent neural network model (PGRNN) that combines RNNs and physics-based models to leverage their complementary strengths and improve the modeling of physical processes. Specifically, we show that a PGRNN can improve prediction accuracy over that of physical models, while generating outputs consistent with physical laws, and achieving good generalizability. Standard RNNs, even when producing superior prediction accuracy, often produce physically inconsistent results and lack generalizability. We further enhance this approach by using a pre-training method that leverages the simulated data from a physics-based model to address the scarcity of observed data. The PGRNN has the flexibility to incorporate additional physical constraints and we incorporate a density-depth relationship. Both enhancements further improve PGRNN performance. Although we present and evaluate this methodology in the context of modeling the dynamics of temperature in lakes, it is applicable more widely to a range of scientific and engineering disciplines where mechanistic (also known as process-based) models are used, e.g., power engineering, climate science, materials science, computational chemistry, and biomedicine. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1810.13075v2-abstract-full').style.display = 'none'; document.getElementById('1810.13075v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 January, 2019; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 30 October, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2018. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1810.02880">arXiv:1810.02880</a> <span> [<a href="https://arxiv.org/pdf/1810.02880">pdf</a>, <a href="https://arxiv.org/format/1810.02880">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"> Physics Guided Recurrent Neural Networks For Modeling Dynamical Systems: Application to Monitoring Water Temperature And Quality In Lakes </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jia%2C+X">Xiaowei Jia</a>, <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</a>, <a href="/search/cs?searchtype=author&query=Willard%2C+J">Jared Willard</a>, <a href="/search/cs?searchtype=author&query=Steinbach%2C+M">Michael Steinbach</a>, <a href="/search/cs?searchtype=author&query=Read%2C+J">Jordan Read</a>, <a href="/search/cs?searchtype=author&query=Hanson%2C+P+C">Paul C Hanson</a>, <a href="/search/cs?searchtype=author&query=Dugan%2C+H+A">Hilary A Dugan</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+V">Vipin Kumar</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1810.02880v1-abstract-short" style="display: inline;"> In this paper, we introduce a novel framework for combining scientific knowledge within physics-based models and recurrent neural networks to advance scientific discovery in many dynamical systems. We will first describe the use of outputs from physics-based models in learning a hybrid-physics-data model. Then, we further incorporate physical knowledge in real-world dynamical systems as additional… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1810.02880v1-abstract-full').style.display = 'inline'; document.getElementById('1810.02880v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1810.02880v1-abstract-full" style="display: none;"> In this paper, we introduce a novel framework for combining scientific knowledge within physics-based models and recurrent neural networks to advance scientific discovery in many dynamical systems. We will first describe the use of outputs from physics-based models in learning a hybrid-physics-data model. Then, we further incorporate physical knowledge in real-world dynamical systems as additional constraints for training recurrent neural networks. We will apply this approach on modeling lake temperature and quality where we take into account the physical constraints along both the depth dimension and time dimension. By using scientific knowledge to guide the construction and learning the data-driven model, we demonstrate that this method can achieve better prediction accuracy as well as scientific consistency of results. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1810.02880v1-abstract-full').style.display = 'none'; document.getElementById('1810.02880v1-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, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2018. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">3 pages, 3 figures, 8th International Workshop on Climate Informatics</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68T01 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1802.06095">arXiv:1802.06095</a> <span> [<a href="https://arxiv.org/pdf/1802.06095">pdf</a>, <a href="https://arxiv.org/ps/1802.06095">ps</a>, <a href="https://arxiv.org/format/1802.06095">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Mining Sub-Interval Relationships In Time Series Data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Agrawal%2C+S">Saurabh Agrawal</a>, <a href="/search/cs?searchtype=author&query=Verma%2C+S">Saurabh Verma</a>, <a href="/search/cs?searchtype=author&query=Atluri%2C+G">Gowtham Atluri</a>, <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</a>, <a href="/search/cs?searchtype=author&query=Liess%2C+S">Stefan Liess</a>, <a href="/search/cs?searchtype=author&query=Macdonald%2C+A">Angus Macdonald III</a>, <a href="/search/cs?searchtype=author&query=Chatterjee%2C+S">Snigdhansu Chatterjee</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+V">Vipin Kumar</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1802.06095v1-abstract-short" style="display: inline;"> Time-series data is being increasingly collected and stud- ied in several areas such as neuroscience, climate science, transportation, and social media. Discovery of complex patterns of relationships between individual time-series, using data-driven approaches can improve our understanding of real-world systems. While traditional approaches typically study relationships between two entire time ser… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1802.06095v1-abstract-full').style.display = 'inline'; document.getElementById('1802.06095v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1802.06095v1-abstract-full" style="display: none;"> Time-series data is being increasingly collected and stud- ied in several areas such as neuroscience, climate science, transportation, and social media. Discovery of complex patterns of relationships between individual time-series, using data-driven approaches can improve our understanding of real-world systems. While traditional approaches typically study relationships between two entire time series, many interesting relationships in real-world applications exist in small sub-intervals of time while remaining absent or feeble during other sub-intervals. In this paper, we define the notion of a sub-interval relationship (SIR) to capture inter- actions between two time series that are prominent only in certain sub-intervals of time. We propose a novel and efficient approach to find most interesting SIR in a pair of time series. We evaluate our proposed approach on two real-world datasets from climate science and neuroscience domain and demonstrated the scalability and computational efficiency of our proposed approach. We further evaluated our discovered SIRs based on a randomization based procedure. Our results indicated the existence of several such relationships that are statistically significant, some of which were also found to have physical interpretation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1802.06095v1-abstract-full').style.display = 'none'; document.getElementById('1802.06095v1-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, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2018. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1712.07203">arXiv:1712.07203</a> <span> [<a href="https://arxiv.org/pdf/1712.07203">pdf</a>, <a href="https://arxiv.org/format/1712.07203">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"> Discovery of Shifting Patterns in Sequence Classification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jia%2C+X">Xiaowei Jia</a>, <a href="/search/cs?searchtype=author&query=Khandelwal%2C+A">Ankush Khandelwal</a>, <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+V">Vipin Kumar</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1712.07203v1-abstract-short" style="display: inline;"> In this paper, we investigate the multi-variate sequence classification problem from a multi-instance learning perspective. Real-world sequential data commonly show discriminative patterns only at specific time periods. For instance, we can identify a cropland during its growing season, but it looks similar to a barren land after harvest or before planting. Besides, even within the same class, the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1712.07203v1-abstract-full').style.display = 'inline'; document.getElementById('1712.07203v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1712.07203v1-abstract-full" style="display: none;"> In this paper, we investigate the multi-variate sequence classification problem from a multi-instance learning perspective. Real-world sequential data commonly show discriminative patterns only at specific time periods. For instance, we can identify a cropland during its growing season, but it looks similar to a barren land after harvest or before planting. Besides, even within the same class, the discriminative patterns can appear in different periods of sequential data. Due to such property, these discriminative patterns are also referred to as shifting patterns. The shifting patterns in sequential data severely degrade the performance of traditional classification methods without sufficient training data. We propose a novel sequence classification method by automatically mining shifting patterns from multi-variate sequence. The method employs a multi-instance learning approach to detect shifting patterns while also modeling temporal relationships within each multi-instance bag by an LSTM model to further improve the classification performance. We extensively evaluate our method on two real-world applications - cropland mapping and affective state recognition. The experiments demonstrate the superiority of our proposed method in sequence classification performance and in detecting discriminative shifting patterns. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1712.07203v1-abstract-full').style.display = 'none'; document.getElementById('1712.07203v1-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 December, 2017; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2017. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1711.05799">arXiv:1711.05799</a> <span> [<a href="https://arxiv.org/pdf/1711.05799">pdf</a>, <a href="https://arxiv.org/format/1711.05799">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="Geophysics">physics.geo-ph</span> </div> </div> <p class="title is-5 mathjax"> ORBIT: Ordering Based Information Transfer Across Space and Time for Global Surface Water Monitoring </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Khandelwal%2C+A">Ankush Khandelwal</a>, <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+V">Vipin Kumar</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1711.05799v1-abstract-short" style="display: inline;"> Many earth science applications require data at both high spatial and temporal resolution for effective monitoring of various ecosystem resources. Due to practical limitations in sensor design, there is often a trade-off in different resolutions of spatio-temporal datasets and hence a single sensor alone cannot provide the required information. Various data fusion methods have been proposed in the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1711.05799v1-abstract-full').style.display = 'inline'; document.getElementById('1711.05799v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1711.05799v1-abstract-full" style="display: none;"> Many earth science applications require data at both high spatial and temporal resolution for effective monitoring of various ecosystem resources. Due to practical limitations in sensor design, there is often a trade-off in different resolutions of spatio-temporal datasets and hence a single sensor alone cannot provide the required information. Various data fusion methods have been proposed in the literature that mainly rely on individual timesteps when both datasets are available to learn a mapping between features values at different resolutions using local relationships between pixels. Earth observation data is often plagued with spatially and temporally correlated noise, outliers and missing data due to atmospheric disturbances which pose a challenge in learning the mapping from a local neighborhood at individual timesteps. In this paper, we aim to exploit time-independent global relationships between pixels for robust transfer of information across different scales. Specifically, we propose a new framework, ORBIT (Ordering Based Information Transfer) that uses relative ordering constraint among pixels to transfer information across both time and scales. The effectiveness of the framework is demonstrated for global surface water monitoring using both synthetic and real-world datasets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1711.05799v1-abstract-full').style.display = 'none'; document.getElementById('1711.05799v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 November, 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/1711.04710">arXiv:1711.04710</a> <span> [<a href="https://arxiv.org/pdf/1711.04710">pdf</a>, <a href="https://arxiv.org/format/1711.04710">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="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Databases">cs.DB</span> </div> </div> <p class="title is-5 mathjax"> Spatio-Temporal Data Mining: A Survey of Problems and Methods </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Atluri%2C+G">Gowtham Atluri</a>, <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+V">Vipin Kumar</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1711.04710v2-abstract-short" style="display: inline;"> Large volumes of spatio-temporal data are increasingly collected and studied in diverse domains including, climate science, social sciences, neuroscience, epidemiology, transportation, mobile health, and Earth sciences. Spatio-temporal data differs from relational data for which computational approaches are developed in the data mining community for multiple decades, in that both spatial and tempo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1711.04710v2-abstract-full').style.display = 'inline'; document.getElementById('1711.04710v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1711.04710v2-abstract-full" style="display: none;"> Large volumes of spatio-temporal data are increasingly collected and studied in diverse domains including, climate science, social sciences, neuroscience, epidemiology, transportation, mobile health, and Earth sciences. Spatio-temporal data differs from relational data for which computational approaches are developed in the data mining community for multiple decades, in that both spatial and temporal attributes are available in addition to the actual measurements/attributes. The presence of these attributes introduces additional challenges that needs to be dealt with. Approaches for mining spatio-temporal data have been studied for over a decade in the data mining community. In this article we present a broad survey of this relatively young field of spatio-temporal data mining. We discuss different types of spatio-temporal data and the relevant data mining questions that arise in the context of analyzing each of these datasets. Based on the nature of the data mining problem studied, we classify literature on spatio-temporal data mining into six major categories: clustering, predictive learning, change detection, frequent pattern mining, anomaly detection, and relationship mining. We discuss the various forms of spatio-temporal data mining problems in each of these categories. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1711.04710v2-abstract-full').style.display = 'none'; document.getElementById('1711.04710v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 November, 2017; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 13 November, 2017; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 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">Accepted for publication at ACM Computing Surveys</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1711.04708">arXiv:1711.04708</a> <span> [<a href="https://arxiv.org/pdf/1711.04708">pdf</a>, <a href="https://arxiv.org/format/1711.04708">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="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Geophysics">physics.geo-ph</span> </div> </div> <p class="title is-5 mathjax"> Machine Learning for the Geosciences: Challenges and Opportunities </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</a>, <a href="/search/cs?searchtype=author&query=Ebert-Uphoff%2C+I">Imme Ebert-Uphoff</a>, <a href="/search/cs?searchtype=author&query=Ravela%2C+S">Sai Ravela</a>, <a href="/search/cs?searchtype=author&query=Babaie%2C+H+A">Hassan Ali Babaie</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+V">Vipin Kumar</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1711.04708v1-abstract-short" style="display: inline;"> Geosciences is a field of great societal relevance that requires solutions to several urgent problems facing our humanity and the planet. As geosciences enters the era of big data, machine learning (ML) -- that has been widely successful in commercial domains -- offers immense potential to contribute to problems in geosciences. However, problems in geosciences have several unique challenges that a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1711.04708v1-abstract-full').style.display = 'inline'; document.getElementById('1711.04708v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1711.04708v1-abstract-full" style="display: none;"> Geosciences is a field of great societal relevance that requires solutions to several urgent problems facing our humanity and the planet. As geosciences enters the era of big data, machine learning (ML) -- that has been widely successful in commercial domains -- offers immense potential to contribute to problems in geosciences. However, problems in geosciences have several unique challenges that are seldom found in traditional applications, requiring novel problem formulations and methodologies in machine learning. This article introduces researchers in the machine learning (ML) community to these challenges offered by geoscience problems and the opportunities that exist for advancing both machine learning and geosciences. We first highlight typical sources of geoscience data and describe their properties that make it challenging to use traditional machine learning techniques. We then describe some of the common categories of geoscience problems where machine learning can play a role, and discuss some of the existing efforts and promising directions for methodological development in machine learning. We conclude by discussing some of the emerging research themes in machine learning that are applicable across all problems in the geosciences, and the importance of a deep collaboration between machine learning and geosciences for synergistic advancements in both disciplines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1711.04708v1-abstract-full').style.display = 'none'; document.getElementById('1711.04708v1-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 November, 2017; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 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">Under review at IEEE Transactions on Knowledge and Data Engineering</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1710.11431">arXiv:1710.11431</a> <span> [<a href="https://arxiv.org/pdf/1710.11431">pdf</a>, <a href="https://arxiv.org/format/1710.11431">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="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Data Analysis, Statistics and Probability">physics.data-an</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"> Physics-guided Neural Networks (PGNN): An Application in Lake Temperature Modeling </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Daw%2C+A">Arka Daw</a>, <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</a>, <a href="/search/cs?searchtype=author&query=Watkins%2C+W">William Watkins</a>, <a href="/search/cs?searchtype=author&query=Read%2C+J">Jordan Read</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+V">Vipin Kumar</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1710.11431v3-abstract-short" style="display: inline;"> This paper introduces a framework for combining scientific knowledge of physics-based models with neural networks to advance scientific discovery. This framework, termed physics-guided neural networks (PGNN), leverages the output of physics-based model simulations along with observational features in a hybrid modeling setup to generate predictions using a neural network architecture. Further, this… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1710.11431v3-abstract-full').style.display = 'inline'; document.getElementById('1710.11431v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1710.11431v3-abstract-full" style="display: none;"> This paper introduces a framework for combining scientific knowledge of physics-based models with neural networks to advance scientific discovery. This framework, termed physics-guided neural networks (PGNN), leverages the output of physics-based model simulations along with observational features in a hybrid modeling setup to generate predictions using a neural network architecture. Further, this framework uses physics-based loss functions in the learning objective of neural networks to ensure that the model predictions not only show lower errors on the training set but are also scientifically consistent with the known physics on the unlabeled set. We illustrate the effectiveness of PGNN for the problem of lake temperature modeling, where physical relationships between the temperature, density, and depth of water are used to design a physics-based loss function. By using scientific knowledge to guide the construction and learning of neural networks, we are able to show that the proposed framework ensures better generalizability as well as scientific consistency of results. All the code and datasets used in this study have been made available on this link \url{https://github.com/arkadaw9/PGNN}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1710.11431v3-abstract-full').style.display = 'none'; document.getElementById('1710.11431v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 September, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 31 October, 2017; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2017. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1612.08544">arXiv:1612.08544</a> <span> [<a href="https://arxiv.org/pdf/1612.08544">pdf</a>, <a href="https://arxiv.org/format/1612.08544">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 class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/TKDE.2017.2720168">10.1109/TKDE.2017.2720168 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Theory-guided Data Science: A New Paradigm for Scientific Discovery from Data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Karpatne%2C+A">Anuj Karpatne</a>, <a href="/search/cs?searchtype=author&query=Atluri%2C+G">Gowtham Atluri</a>, <a href="/search/cs?searchtype=author&query=Faghmous%2C+J">James Faghmous</a>, <a href="/search/cs?searchtype=author&query=Steinbach%2C+M">Michael Steinbach</a>, <a href="/search/cs?searchtype=author&query=Banerjee%2C+A">Arindam Banerjee</a>, <a href="/search/cs?searchtype=author&query=Ganguly%2C+A">Auroop Ganguly</a>, <a href="/search/cs?searchtype=author&query=Shekhar%2C+S">Shashi Shekhar</a>, <a href="/search/cs?searchtype=author&query=Samatova%2C+N">Nagiza Samatova</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+V">Vipin Kumar</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1612.08544v2-abstract-short" style="display: inline;"> Data science models, although successful in a number of commercial domains, have had limited applicability in scientific problems involving complex physical phenomena. Theory-guided data science (TGDS) is an emerging paradigm that aims to leverage the wealth of scientific knowledge for improving the effectiveness of data science models in enabling scientific discovery. The overarching vision of TG… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1612.08544v2-abstract-full').style.display = 'inline'; document.getElementById('1612.08544v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1612.08544v2-abstract-full" style="display: none;"> Data science models, although successful in a number of commercial domains, have had limited applicability in scientific problems involving complex physical phenomena. Theory-guided data science (TGDS) is an emerging paradigm that aims to leverage the wealth of scientific knowledge for improving the effectiveness of data science models in enabling scientific discovery. The overarching vision of TGDS is to introduce scientific consistency as an essential component for learning generalizable models. Further, by producing scientifically interpretable models, TGDS aims to advance our scientific understanding by discovering novel domain insights. Indeed, the paradigm of TGDS has started to gain prominence in a number of scientific disciplines such as turbulence modeling, material discovery, quantum chemistry, bio-medical science, bio-marker discovery, climate science, and hydrology. In this paper, we formally conceptualize the paradigm of TGDS and present a taxonomy of research themes in TGDS. We describe several approaches for integrating domain knowledge in different research themes using illustrative examples from different disciplines. We also highlight some of the promising avenues of novel research for realizing the full potential of theory-guided data science. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1612.08544v2-abstract-full').style.display = 'none'; document.getElementById('1612.08544v2-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 November, 2017; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 27 December, 2016; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2016. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> IEEE Transactions on Knowledge and Data Engineering, 29(10), pp.2318-2331. 2017 </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