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 1–11 of 11 results for author: <span class="mathjax">Danel, T</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=Danel%2C+T">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="Danel, T"> </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=Danel%2C+T&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="Danel, T"> <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/2410.08938">arXiv:2410.08938</a> <span> [<a href="https://arxiv.org/pdf/2410.08938">pdf</a>, <a href="https://arxiv.org/format/2410.08938">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantitative Methods">q-bio.QM</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"> KinDEL: DNA-Encoded Library Dataset for Kinase Inhibitors </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+B">Benson Chen</a>, <a href="/search/cs?searchtype=author&query=Danel%2C+T">Tomasz Danel</a>, <a href="/search/cs?searchtype=author&query=McEnaney%2C+P+J">Patrick J. McEnaney</a>, <a href="/search/cs?searchtype=author&query=Jain%2C+N">Nikhil Jain</a>, <a href="/search/cs?searchtype=author&query=Novikov%2C+K">Kirill Novikov</a>, <a href="/search/cs?searchtype=author&query=Akki%2C+S+U">Spurti Umesh Akki</a>, <a href="/search/cs?searchtype=author&query=Turnbull%2C+J+L">Joshua L. Turnbull</a>, <a href="/search/cs?searchtype=author&query=Pandya%2C+V+A">Virja Atul Pandya</a>, <a href="/search/cs?searchtype=author&query=Belotserkovskii%2C+B+P">Boris P. Belotserkovskii</a>, <a href="/search/cs?searchtype=author&query=Weaver%2C+J+B">Jared Bryce Weaver</a>, <a href="/search/cs?searchtype=author&query=Biswas%2C+A">Ankita Biswas</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+D">Dat Nguyen</a>, <a href="/search/cs?searchtype=author&query=Dreiman%2C+G+H+S">Gabriel H. S. Dreiman</a>, <a href="/search/cs?searchtype=author&query=Sultan%2C+M">Mohammad Sultan</a>, <a href="/search/cs?searchtype=author&query=Stanley%2C+N">Nathaniel Stanley</a>, <a href="/search/cs?searchtype=author&query=Whalen%2C+D+M">Daniel M Whalen</a>, <a href="/search/cs?searchtype=author&query=Kanichar%2C+D">Divya Kanichar</a>, <a href="/search/cs?searchtype=author&query=Klein%2C+C">Christoph Klein</a>, <a href="/search/cs?searchtype=author&query=Fox%2C+E">Emily Fox</a>, <a href="/search/cs?searchtype=author&query=Watts%2C+R+E">R. Edward Watts</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="2410.08938v1-abstract-short" style="display: inline;"> DNA-Encoded Libraries (DEL) are combinatorial small molecule libraries that offer an efficient way to characterize diverse chemical spaces. Selection experiments using DELs are pivotal to drug discovery efforts, enabling high-throughput screens for hit finding. However, limited availability of public DEL datasets hinders the advancement of computational techniques designed to process such data. To… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.08938v1-abstract-full').style.display = 'inline'; document.getElementById('2410.08938v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.08938v1-abstract-full" style="display: none;"> DNA-Encoded Libraries (DEL) are combinatorial small molecule libraries that offer an efficient way to characterize diverse chemical spaces. Selection experiments using DELs are pivotal to drug discovery efforts, enabling high-throughput screens for hit finding. However, limited availability of public DEL datasets hinders the advancement of computational techniques designed to process such data. To bridge this gap, we present KinDEL, one of the first large, publicly available DEL datasets on two kinases: Mitogen-Activated Protein Kinase 14 (MAPK14) and Discoidin Domain Receptor Tyrosine Kinase 1 (DDR1). Interest in this data modality is growing due to its ability to generate extensive supervised chemical data that densely samples around select molecular structures. Demonstrating one such application of the data, we benchmark different machine learning techniques to develop predictive models for hit identification; in particular, we highlight recent structure-based probabilistic approaches. Finally, we provide biophysical assay data, both on- and off-DNA, to validate our models on a smaller subset of molecules. Data and code for our benchmarks can be found at: https://github.com/insitro/kindel. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.08938v1-abstract-full').style.display = 'none'; document.getElementById('2410.08938v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.13944">arXiv:2312.13944</a> <span> [<a href="https://arxiv.org/pdf/2312.13944">pdf</a>, <a href="https://arxiv.org/format/2312.13944">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Biomolecules">q-bio.BM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1016/j.drudis.2022.103439">10.1016/j.drudis.2022.103439 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Docking-based generative approaches in the search for new drug candidates </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Danel%2C+T">Tomasz Danel</a>, <a href="/search/cs?searchtype=author&query=%C5%81%C4%99ski%2C+J">Jan 艁臋ski</a>, <a href="/search/cs?searchtype=author&query=Podlewska%2C+S">Sabina Podlewska</a>, <a href="/search/cs?searchtype=author&query=Podolak%2C+I+T">Igor T. Podolak</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2312.13944v1-abstract-short" style="display: inline;"> Despite the great popularity of virtual screening of existing compound libraries, the search for new potential drug candidates also takes advantage of generative protocols, where new compound suggestions are enumerated using various algorithms. To increase the activity potency of generative approaches, they have recently been coupled with molecular docking, a leading methodology of structure-based… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.13944v1-abstract-full').style.display = 'inline'; document.getElementById('2312.13944v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.13944v1-abstract-full" style="display: none;"> Despite the great popularity of virtual screening of existing compound libraries, the search for new potential drug candidates also takes advantage of generative protocols, where new compound suggestions are enumerated using various algorithms. To increase the activity potency of generative approaches, they have recently been coupled with molecular docking, a leading methodology of structure-based drug design. In this review, we summarize progress since docking-based generative models emerged. We propose a new taxonomy for these methods and discuss their importance for the field of computer-aided drug design. In addition, we discuss the most promising directions for further development of generative protocols coupled with docking. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.13944v1-abstract-full').style.display = 'none'; document.getElementById('2312.13944v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Drug Discovery Today 28.2 (2023) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2210.03745">arXiv:2210.03745</a> <span> [<a href="https://arxiv.org/pdf/2210.03745">pdf</a>, <a href="https://arxiv.org/format/2210.03745">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantitative Methods">q-bio.QM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> ProGReST: Prototypical Graph Regression Soft Trees for Molecular Property Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rymarczyk%2C+D">Dawid Rymarczyk</a>, <a href="/search/cs?searchtype=author&query=Dobrowolski%2C+D">Daniel Dobrowolski</a>, <a href="/search/cs?searchtype=author&query=Danel%2C+T">Tomasz Danel</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2210.03745v2-abstract-short" style="display: inline;"> In this work, we propose the novel Prototypical Graph Regression Self-explainable Trees (ProGReST) model, which combines prototype learning, soft decision trees, and Graph Neural Networks. In contrast to other works, our model can be used to address various challenging tasks, including compound property prediction. In ProGReST, the rationale is obtained along with prediction due to the model's bui… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.03745v2-abstract-full').style.display = 'inline'; document.getElementById('2210.03745v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2210.03745v2-abstract-full" style="display: none;"> In this work, we propose the novel Prototypical Graph Regression Self-explainable Trees (ProGReST) model, which combines prototype learning, soft decision trees, and Graph Neural Networks. In contrast to other works, our model can be used to address various challenging tasks, including compound property prediction. In ProGReST, the rationale is obtained along with prediction due to the model's built-in interpretability. Additionally, we introduce a new graph prototype projection to accelerate model training. Finally, we evaluate PRoGReST on a wide range of chemical datasets for molecular property prediction and perform in-depth analysis with chemical experts to evaluate obtained interpretations. Our method achieves competitive results against state-of-the-art methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.03745v2-abstract-full').style.display = 'none'; document.getElementById('2210.03745v2-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 December, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 7 October, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to SDM2023</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2110.05841">arXiv:2110.05841</a> <span> [<a href="https://arxiv.org/pdf/2110.05841">pdf</a>, <a href="https://arxiv.org/format/2110.05841">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"> Relative Molecule Self-Attention Transformer </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Maziarka%2C+%C5%81">艁ukasz Maziarka</a>, <a href="/search/cs?searchtype=author&query=Majchrowski%2C+D">Dawid Majchrowski</a>, <a href="/search/cs?searchtype=author&query=Danel%2C+T">Tomasz Danel</a>, <a href="/search/cs?searchtype=author&query=Gai%C5%84ski%2C+P">Piotr Gai艅ski</a>, <a href="/search/cs?searchtype=author&query=Tabor%2C+J">Jacek Tabor</a>, <a href="/search/cs?searchtype=author&query=Podolak%2C+I">Igor Podolak</a>, <a href="/search/cs?searchtype=author&query=Morkisz%2C+P">Pawe艂 Morkisz</a>, <a href="/search/cs?searchtype=author&query=Jastrz%C4%99bski%2C+S">Stanis艂aw Jastrz臋bski</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="2110.05841v1-abstract-short" style="display: inline;"> Self-supervised learning holds promise to revolutionize molecule property prediction - a central task to drug discovery and many more industries - by enabling data efficient learning from scarce experimental data. Despite significant progress, non-pretrained methods can be still competitive in certain settings. We reason that architecture might be a key bottleneck. In particular, enriching the bac… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2110.05841v1-abstract-full').style.display = 'inline'; document.getElementById('2110.05841v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2110.05841v1-abstract-full" style="display: none;"> Self-supervised learning holds promise to revolutionize molecule property prediction - a central task to drug discovery and many more industries - by enabling data efficient learning from scarce experimental data. Despite significant progress, non-pretrained methods can be still competitive in certain settings. We reason that architecture might be a key bottleneck. In particular, enriching the backbone architecture with domain-specific inductive biases has been key for the success of self-supervised learning in other domains. In this spirit, we methodologically explore the design space of the self-attention mechanism tailored to molecular data. We identify a novel variant of self-attention adapted to processing molecules, inspired by the relative self-attention layer, which involves fusing embedded graph and distance relationships between atoms. Our main contribution is Relative Molecule Attention Transformer (R-MAT): a novel Transformer-based model based on the developed self-attention layer that achieves state-of-the-art or very competitive results across a~wide range of molecule property prediction tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2110.05841v1-abstract-full').style.display = 'none'; document.getElementById('2110.05841v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 October, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2107.13214">arXiv:2107.13214</a> <span> [<a href="https://arxiv.org/pdf/2107.13214">pdf</a>, <a href="https://arxiv.org/format/2107.13214">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"> SONG: Self-Organizing Neural Graphs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Struski%2C+%C5%81">艁ukasz Struski</a>, <a href="/search/cs?searchtype=author&query=Danel%2C+T">Tomasz Danel</a>, <a href="/search/cs?searchtype=author&query=%C5%9Amieja%2C+M">Marek 艢mieja</a>, <a href="/search/cs?searchtype=author&query=Tabor%2C+J">Jacek Tabor</a>, <a href="/search/cs?searchtype=author&query=Zieli%C5%84ski%2C+B">Bartosz Zieli艅ski</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="2107.13214v1-abstract-short" style="display: inline;"> Recent years have seen a surge in research on deep interpretable neural networks with decision trees as one of the most commonly incorporated tools. There are at least three advantages of using decision trees over logistic regression classification models: they are easy to interpret since they are based on binary decisions, they can make decisions faster, and they provide a hierarchy of classes. H… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2107.13214v1-abstract-full').style.display = 'inline'; document.getElementById('2107.13214v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2107.13214v1-abstract-full" style="display: none;"> Recent years have seen a surge in research on deep interpretable neural networks with decision trees as one of the most commonly incorporated tools. There are at least three advantages of using decision trees over logistic regression classification models: they are easy to interpret since they are based on binary decisions, they can make decisions faster, and they provide a hierarchy of classes. However, one of the well-known drawbacks of decision trees, as compared to decision graphs, is that decision trees cannot reuse the decision nodes. Nevertheless, decision graphs were not commonly used in deep learning due to the lack of efficient gradient-based training techniques. In this paper, we fill this gap and provide a general paradigm based on Markov processes, which allows for efficient training of the special type of decision graphs, which we call Self-Organizing Neural Graphs (SONG). We provide an extensive theoretical study of SONG, complemented by experiments conducted on Letter, Connect4, MNIST, CIFAR, and TinyImageNet datasets, showing that our method performs on par or better than existing decision models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2107.13214v1-abstract-full').style.display = 'none'; document.getElementById('2107.13214v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 July, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2012.04444">arXiv:2012.04444</a> <span> [<a href="https://arxiv.org/pdf/2012.04444">pdf</a>, <a href="https://arxiv.org/format/2012.04444">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Chemical Physics">physics.chem-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Comparison of Atom Representations in Graph Neural Networks for Molecular Property Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pocha%2C+A">Agnieszka Pocha</a>, <a href="/search/cs?searchtype=author&query=Danel%2C+T">Tomasz Danel</a>, <a href="/search/cs?searchtype=author&query=Maziarka%2C+%C5%81">艁ukasz Maziarka</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="2012.04444v2-abstract-short" style="display: inline;"> Graph neural networks have recently become a standard method for analysing chemical compounds. In the field of molecular property prediction, the emphasis is now put on designing new model architectures, and the importance of atom featurisation is oftentimes belittled. When contrasting two graph neural networks, the use of different atom features possibly leads to the incorrect attribution of the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2012.04444v2-abstract-full').style.display = 'inline'; document.getElementById('2012.04444v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2012.04444v2-abstract-full" style="display: none;"> Graph neural networks have recently become a standard method for analysing chemical compounds. In the field of molecular property prediction, the emphasis is now put on designing new model architectures, and the importance of atom featurisation is oftentimes belittled. When contrasting two graph neural networks, the use of different atom features possibly leads to the incorrect attribution of the results to the network architecture. To provide a better understanding of this issue, we compare multiple atom representations for graph models and evaluate them on the prediction of free energy, solubility, and metabolic stability. To the best of our knowledge, this is the first methodological study that focuses on the relevance of atom representation to the predictive performance of graph neural networks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2012.04444v2-abstract-full').style.display = 'none'; document.getElementById('2012.04444v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 February, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 23 November, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 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">Machine Learning for Molecules Workshop at NeurIPS 2020 (spotlight talk)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2010.13914">arXiv:2010.13914</a> <span> [<a href="https://arxiv.org/pdf/2010.13914">pdf</a>, <a href="https://arxiv.org/format/2010.13914">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Processing of incomplete images by (graph) convolutional neural networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Danel%2C+T">Tomasz Danel</a>, <a href="/search/cs?searchtype=author&query=%C5%9Amieja%2C+M">Marek 艢mieja</a>, <a href="/search/cs?searchtype=author&query=Struski%2C+%C5%81">艁ukasz Struski</a>, <a href="/search/cs?searchtype=author&query=Spurek%2C+P">Przemys艂aw Spurek</a>, <a href="/search/cs?searchtype=author&query=Maziarka%2C+%C5%81">艁ukasz Maziarka</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="2010.13914v1-abstract-short" style="display: inline;"> We investigate the problem of training neural networks from incomplete images without replacing missing values. For this purpose, we first represent an image as a graph, in which missing pixels are entirely ignored. The graph image representation is processed using a spatial graph convolutional network (SGCN) -- a type of graph convolutional networks, which is a proper generalization of classical… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2010.13914v1-abstract-full').style.display = 'inline'; document.getElementById('2010.13914v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2010.13914v1-abstract-full" style="display: none;"> We investigate the problem of training neural networks from incomplete images without replacing missing values. For this purpose, we first represent an image as a graph, in which missing pixels are entirely ignored. The graph image representation is processed using a spatial graph convolutional network (SGCN) -- a type of graph convolutional networks, which is a proper generalization of classical CNNs operating on images. On one hand, our approach avoids the problem of missing data imputation while, on the other hand, there is a natural correspondence between CNNs and SGCN. Experiments confirm that our approach performs better than analogical CNNs with the imputation of missing values on typical classification and reconstruction tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2010.13914v1-abstract-full').style.display = 'none'; document.getElementById('2010.13914v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 October, 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/2006.16955">arXiv:2006.16955</a> <span> [<a href="https://arxiv.org/pdf/2006.16955">pdf</a>, <a href="https://arxiv.org/format/2006.16955">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Biomolecules">q-bio.BM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> <div 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/10.1021/acs.jcim.2c01355">10.1021/acs.jcim.2c01355 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> We Should at Least Be Able to Design Molecules That Dock Well </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Cieplinski%2C+T">Tobiasz Cieplinski</a>, <a href="/search/cs?searchtype=author&query=Danel%2C+T">Tomasz Danel</a>, <a href="/search/cs?searchtype=author&query=Podlewska%2C+S">Sabina Podlewska</a>, <a href="/search/cs?searchtype=author&query=Jastrzebski%2C+S">Stanislaw Jastrzebski</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2006.16955v5-abstract-short" style="display: inline;"> Designing compounds with desired properties is a key element of the drug discovery process. However, measuring progress in the field has been challenging due to the lack of realistic retrospective benchmarks, and the large cost of prospective validation. To close this gap, we propose a benchmark based on docking, a popular computational method for assessing molecule binding to a protein. Concretel… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2006.16955v5-abstract-full').style.display = 'inline'; document.getElementById('2006.16955v5-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2006.16955v5-abstract-full" style="display: none;"> Designing compounds with desired properties is a key element of the drug discovery process. However, measuring progress in the field has been challenging due to the lack of realistic retrospective benchmarks, and the large cost of prospective validation. To close this gap, we propose a benchmark based on docking, a popular computational method for assessing molecule binding to a protein. Concretely, the goal is to generate drug-like molecules that are scored highly by SMINA, a popular docking software. We observe that popular graph-based generative models fail to generate molecules with a high docking score when trained using a realistically sized training set. This suggests a limitation of the current incarnation of models for de novo drug design. Finally, we propose a simplified version of the benchmark based on a simpler scoring function, and show that the tested models are able to partially solve it. We release the benchmark as an easy to use package available at https://github.com/cieplinski-tobiasz/smina-docking-benchmark. We hope that our benchmark will serve as a stepping stone towards the goal of automatically generating promising drug candidates. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2006.16955v5-abstract-full').style.display = 'none'; document.getElementById('2006.16955v5-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 June, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2020. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Published in Journal of Chemical Information and Modeling</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2002.08264">arXiv:2002.08264</a> <span> [<a href="https://arxiv.org/pdf/2002.08264">pdf</a>, <a href="https://arxiv.org/format/2002.08264">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"> Molecule Attention Transformer </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Maziarka%2C+%C5%81">艁ukasz Maziarka</a>, <a href="/search/cs?searchtype=author&query=Danel%2C+T">Tomasz Danel</a>, <a href="/search/cs?searchtype=author&query=Mucha%2C+S">S艂awomir Mucha</a>, <a href="/search/cs?searchtype=author&query=Rataj%2C+K">Krzysztof Rataj</a>, <a href="/search/cs?searchtype=author&query=Tabor%2C+J">Jacek Tabor</a>, <a href="/search/cs?searchtype=author&query=Jastrz%C4%99bski%2C+S">Stanis艂aw Jastrz臋bski</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="2002.08264v1-abstract-short" style="display: inline;"> Designing a single neural network architecture that performs competitively across a range of molecule property prediction tasks remains largely an open challenge, and its solution may unlock a widespread use of deep learning in the drug discovery industry. To move towards this goal, we propose Molecule Attention Transformer (MAT). Our key innovation is to augment the attention mechanism in Transfo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2002.08264v1-abstract-full').style.display = 'inline'; document.getElementById('2002.08264v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2002.08264v1-abstract-full" style="display: none;"> Designing a single neural network architecture that performs competitively across a range of molecule property prediction tasks remains largely an open challenge, and its solution may unlock a widespread use of deep learning in the drug discovery industry. To move towards this goal, we propose Molecule Attention Transformer (MAT). Our key innovation is to augment the attention mechanism in Transformer using inter-atomic distances and the molecular graph structure. Experiments show that MAT performs competitively on a diverse set of molecular prediction tasks. Most importantly, with a simple self-supervised pretraining, MAT requires tuning of only a few hyperparameter values to achieve state-of-the-art performance on downstream tasks. Finally, we show that attention weights learned by MAT are interpretable from the chemical point of view. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2002.08264v1-abstract-full').style.display = 'none'; document.getElementById('2002.08264v1-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 February, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2020. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Graph Representation Learning workshop and Machine Learning and the Physical Sciences workshop at NeurIPS 2019 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1909.05310">arXiv:1909.05310</a> <span> [<a href="https://arxiv.org/pdf/1909.05310">pdf</a>, <a href="https://arxiv.org/format/1909.05310">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"> Spatial Graph Convolutional Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Danel%2C+T">Tomasz Danel</a>, <a href="/search/cs?searchtype=author&query=Spurek%2C+P">Przemys艂aw Spurek</a>, <a href="/search/cs?searchtype=author&query=Tabor%2C+J">Jacek Tabor</a>, <a href="/search/cs?searchtype=author&query=%C5%9Amieja%2C+M">Marek 艢mieja</a>, <a href="/search/cs?searchtype=author&query=Struski%2C+%C5%81">艁ukasz Struski</a>, <a href="/search/cs?searchtype=author&query=S%C5%82owik%2C+A">Agnieszka S艂owik</a>, <a href="/search/cs?searchtype=author&query=Maziarka%2C+%C5%81">艁ukasz Maziarka</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1909.05310v2-abstract-short" style="display: inline;"> Graph Convolutional Networks (GCNs) have recently become the primary choice for learning from graph-structured data, superseding hash fingerprints in representing chemical compounds. However, GCNs lack the ability to take into account the ordering of node neighbors, even when there is a geometric interpretation of the graph vertices that provides an order based on their spatial positions. To remed… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1909.05310v2-abstract-full').style.display = 'inline'; document.getElementById('1909.05310v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1909.05310v2-abstract-full" style="display: none;"> Graph Convolutional Networks (GCNs) have recently become the primary choice for learning from graph-structured data, superseding hash fingerprints in representing chemical compounds. However, GCNs lack the ability to take into account the ordering of node neighbors, even when there is a geometric interpretation of the graph vertices that provides an order based on their spatial positions. To remedy this issue, we propose Spatial Graph Convolutional Network (SGCN) which uses spatial features to efficiently learn from graphs that can be naturally located in space. Our contribution is threefold: we propose a GCN-inspired architecture which (i) leverages node positions, (ii) is a proper generalization of both GCNs and Convolutional Neural Networks (CNNs), (iii) benefits from augmentation which further improves the performance and assures invariance with respect to the desired properties. Empirically, SGCN outperforms state-of-the-art graph-based methods on image classification and chemical tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1909.05310v2-abstract-full').style.display = 'none'; document.getElementById('1909.05310v2-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 July, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 11 September, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1904.03445">arXiv:1904.03445</a> <span> [<a href="https://arxiv.org/pdf/1904.03445">pdf</a>, <a href="https://arxiv.org/format/1904.03445">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/10.1109/TNNLS.2023.3251848">10.1109/TNNLS.2023.3251848 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Feature-Based Interpolation and Geodesics in the Latent Spaces of Generative Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Struski%2C+%C5%81">艁ukasz Struski</a>, <a href="/search/cs?searchtype=author&query=Sadowski%2C+M">Micha艂 Sadowski</a>, <a href="/search/cs?searchtype=author&query=Danel%2C+T">Tomasz Danel</a>, <a href="/search/cs?searchtype=author&query=Tabor%2C+J">Jacek Tabor</a>, <a href="/search/cs?searchtype=author&query=Podolak%2C+I+T">Igor T. Podolak</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1904.03445v3-abstract-short" style="display: inline;"> Interpolating between points is a problem connected simultaneously with finding geodesics and study of generative models. In the case of geodesics, we search for the curves with the shortest length, while in the case of generative models we typically apply linear interpolation in the latent space. However, this interpolation uses implicitly the fact that Gaussian is unimodal. Thus the problem of i… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1904.03445v3-abstract-full').style.display = 'inline'; document.getElementById('1904.03445v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1904.03445v3-abstract-full" style="display: none;"> Interpolating between points is a problem connected simultaneously with finding geodesics and study of generative models. In the case of geodesics, we search for the curves with the shortest length, while in the case of generative models we typically apply linear interpolation in the latent space. However, this interpolation uses implicitly the fact that Gaussian is unimodal. Thus the problem of interpolating in the case when the latent density is non-Gaussian is an open problem. In this paper, we present a general and unified approach to interpolation, which simultaneously allows us to search for geodesics and interpolating curves in latent space in the case of arbitrary density. Our results have a strong theoretical background based on the introduced quality measure of an interpolating curve. In particular, we show that maximising the quality measure of the curve can be equivalently understood as a search of geodesic for a certain redefinition of the Riemannian metric on the space. We provide examples in three important cases. First, we show that our approach can be easily applied to finding geodesics on manifolds. Next, we focus our attention in finding interpolations in pre-trained generative models. We show that our model effectively works in the case of arbitrary density. Moreover, we can interpolate in the subset of the space consisting of data possessing a given feature. The last case is focused on finding interpolation in the space of chemical compounds. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1904.03445v3-abstract-full').style.display = 'none'; document.getElementById('1904.03445v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 6 April, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> IEEE Transactions on Neural Networks and Learning Systems, 2023 </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