CINXE.COM

<!doctype html> <html lang="en"> <head> <meta charset="utf-8"> <meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no"> <script> const GTAG_ENABLED = true ; const GTAG_TRACKING_ID = "UA-121182717-1"; const SENTRY_DSN_FRONTEND = "".trim(); const GLOBAL_CSRF_TOKEN = 'BYFVxdYwv0KYUM1RTsvHUkxijbyX2Kzv1OJ4uoSJrmho6JHhqWnHRJB5G2dOGmYL'; const MEDIA_URL = "https://production-media.paperswithcode.com/"; const ASSETS_URL = "https://production-assets.paperswithcode.com"; run_after_frontend_loaded = window.run_after_frontend_loaded || []; </script> <link rel="preconnect" href="https://production-assets.paperswithcode.com"><link rel="dns-prefetch" href="https://production-assets.paperswithcode.com"><link rel="preload" as="font" type="font/woff2" href="https://production-assets.paperswithcode.com/perf/fonts/65e877e527022735c1a1.woff2" crossorigin><link rel="preload" as="font" type="font/woff2" href="https://production-assets.paperswithcode.com/perf/fonts/917632e36982ca7933c8.woff2" crossorigin><link rel="preload" as="font" type="font/woff2" href="https://production-assets.paperswithcode.com/perf/fonts/f1405bd8a987c2ea8a67.woff2" crossorigin><script>(()=>{if(GTAG_ENABLED){const t=document.createElement("script");function n(){window.dataLayer.push(arguments)}t.src=`https://www.googletagmanager.com/gtag/js?id=${GTAG_TRACKING_ID}`,document.head.appendChild(t),window.dataLayer=window.dataLayer||[],window.gtag=n,n("js",new Date),n("config",GTAG_TRACKING_ID),window.captureOutboundLink=function(t){n("event","click",{event_category:"outbound",event_label:t})}}else window.captureOutboundLink=function(n){document.location=n}})();</script><link rel="preload" as="script" href="https://production-assets.paperswithcode.com/perf/766.4af6b88b.js"><link rel="preload" as="script" href="https://production-assets.paperswithcode.com/perf/2.6da00df7.js"><link rel="preload" as="script" href="https://production-assets.paperswithcode.com/perf/351.a22a9607.js"><link rel="preload" as="script" href="https://production-assets.paperswithcode.com/perf/452.d3ecdfa4.js"><link rel="preload" as="style" href="https://production-assets.paperswithcode.com/perf/553.4050647d.css"><link rel="preload" as="script" href="https://production-assets.paperswithcode.com/perf/553.357efc0e.js"><link rel="preload" as="style" href="https://production-assets.paperswithcode.com/perf/918.c41196c3.css"><link rel="preload" as="style" href="https://production-assets.paperswithcode.com/perf/sota.table.fe0fcc15.css"><link rel="preload" as="script" href="https://production-assets.paperswithcode.com/perf/sota.table.040f2c99.js"><link rel="stylesheet" href="https://production-assets.paperswithcode.com/perf/553.4050647d.css"><link rel="stylesheet" href="https://production-assets.paperswithcode.com/perf/918.c41196c3.css"><link rel="stylesheet" href="https://production-assets.paperswithcode.com/perf/sota.table.fe0fcc15.css">  <title>ogbl-ddi Benchmark (Link Property Prediction) | Papers With Code</title> <meta name="description" content="The current state-of-the-art on ogbl-ddi is ELGNN. See a full comparison of 31 papers with code." />  <meta property="og:title" content="Papers with Code - ogbl-ddi Benchmark (Link Property Prediction)"> <meta property="og:description" content="The current state-of-the-art on ogbl-ddi is ELGNN. See a full comparison of 31 papers with code."> <meta property="og:image" content="https://production-media.paperswithcode.com/sota-thumbs/link-property-prediction-on-ogbl-ddi-large_298a2dc9.png"> <meta property="og:url" content="https://paperswithcode.com/sota/link-property-prediction-on-ogbl-ddi">  <meta name="twitter:card" content="summary_large_image"> <meta name="twitter:site" content="@paperswithcode"> <meta name="twitter:title" content="Papers with Code - ogbl-ddi Benchmark (Link Property Prediction)"> <meta name="twitter:description" content="The current state-of-the-art on ogbl-ddi is ELGNN. See a full comparison of 31 papers with code."> <meta name="twitter:creator" content="@paperswithcode"> <meta name="twitter:url" content="https://paperswithcode.com/sota/link-property-prediction-on-ogbl-ddi"> <meta name="twitter:domain" content="paperswithcode.com">  <script type="application/ld+json">{ "@context": "http://schema.org", "@graph": { "@type": "ItemList", "name": "ogbl-ddi Benchmark (Link Property Prediction)", "description": "The current state-of-the-art on ogbl-ddi is ELGNN. See a full comparison of 31 papers with code.", "url": "https://paperswithcode.com/sota/link-property-prediction-on-ogbl-ddi", "image": "https://production-media.paperswithcode.com/sota-thumbs/link-property-prediction-on-ogbl-ddi-large_298a2dc9.png" } }</script> <meta name="theme-color" content="#fff"/> <link rel="manifest" href="https://production-assets.paperswithcode.com/static/manifest.web.json"> </head> <body> <nav class="navbar navbar-expand-lg navbar-light header"> <a class="navbar-brand" href="/"> <span class=" icon-wrapper" data-name="pwc"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512"><path d="M88 128h48v256H88zm144 0h48v256h-48zm-72 16h48v224h-48zm144 0h48v224h-48zm72-16h48v256h-48z"/><path d="M104 104V56H16v400h88v-48H64V104zm304-48v48h40v304h-40v48h88V56z"/></svg></span> </a> <div class="navbar-mobile-twitter d-lg-none"> <a rel="noreferrer" href="https://twitter.com/paperswithcode"> <span class=" icon-wrapper icon-fa icon-fa-brands" data-name="twitter"><svg viewBox="0 0 512.001 515.25" xmlns="http://www.w3.org/2000/svg"><path d="M459.37 152.016c.326 4.548.326 9.097.326 13.645 0 138.72-105.583 298.558-298.559 298.558C101.685 464.22 46.457 447 0 417.114c8.447.973 16.568 1.298 25.34 1.298 49.054 0 94.213-16.568 130.274-44.832-46.132-.975-84.792-31.188-98.113-72.772 6.499.975 12.996 1.624 19.819 1.624 9.42 0 18.843-1.3 27.613-3.573-48.08-9.747-84.142-51.98-84.142-102.984v-1.3c13.968 7.798 30.213 12.67 47.43 13.32-28.263-18.843-46.78-51.006-46.78-87.391 0-19.492 5.196-37.36 14.294-52.954 51.654 63.674 129.3 105.258 216.364 109.807-1.624-7.797-2.599-15.918-2.599-24.04 0-57.827 46.782-104.934 104.934-104.934 30.214 0 57.502 12.67 76.671 33.136 23.715-4.548 46.455-13.319 66.599-25.34-7.798 24.367-24.366 44.834-46.132 57.828 21.117-2.274 41.584-8.122 60.426-16.244-14.292 20.791-32.161 39.309-52.628 54.253z"/></svg></span> </a> </div> <button class="navbar-toggler" type="button" data-toggle="collapse" data-bs-toggle="collapse" data-target="#top-menu" data-bs-target="#top-menu" aria-controls="top-menu" aria-expanded="false" aria-label="Toggle navigation" > <span class="navbar-toggler-icon"></span> </button> <div class="collapse navbar-collapse" id="top-menu"> <ul class="navbar-nav mr-auto navbar-nav__left light-header"> <li class="nav-item header-search"> <form action="/search" method="get" id="id_global_search_form" autocomplete="off"> <input type="text" name="q_meta" style="display:none" id="q_meta" /> <input type="hidden" name="q_type" id="q_type" /> <input id="id_global_search_input" autocomplete="off" value="" name='q' class="global-search" type="search" placeholder='Search'/> <button type="submit" class="icon"><span class=" icon-wrapper icon-fa icon-fa-light" data-name="search"><svg viewBox="0 0 512.025 520.146" xmlns="http://www.w3.org/2000/svg"><path d="M508.5 482.6c4.7 4.7 4.7 12.3 0 17l-9.9 9.9c-4.7 4.7-12.3 4.7-17 0l-129-129c-2.2-2.3-3.5-5.3-3.5-8.5v-10.2C312 396 262.5 417 208 417 93.1 417 0 323.9 0 209S93.1 1 208 1s208 93.1 208 208c0 54.5-21 104-55.3 141.1H371c3.2 0 6.2 1.2 8.5 3.5zM208 385c97.3 0 176-78.7 176-176S305.3 33 208 33 32 111.7 32 209s78.7 176 176 176z"/></svg></span></button> </form> </li> <li class="nav-item"> <a class="nav-link" href="/sota"> Browse State-of-the-Art </a> </li> <li class="nav-item"> <a class="nav-link" href="/datasets"> Datasets </a> </li> <li class="nav-item"> <a class="nav-link" href="/methods">Methods</a> </li> <li class="nav-item dropdown"> <a class="nav-link dropdown-toggle" role="button" id="navbarDropdownRepro" data-toggle="dropdown" data-bs-toggle="dropdown" aria-haspopup="true" aria-expanded="false" > More </a> <div class="dropdown-menu" aria-labelledby="navbarDropdownRepro"> <a class="dropdown-item" href="/newsletter">Newsletter</a> <a class="dropdown-item" href="/rc2022">RC2022</a> <div class="dropdown-divider"></div> <a class="dropdown-item" href="/about">About</a> <a class="dropdown-item" href="/trends">Trends</a> <a class="dropdown-item" href="https://portal.paperswithcode.com/"> Portals </a> <a class="dropdown-item" href="/libraries"> Libraries </a> </div> </li> </ul> <ul class="navbar-nav ml-auto navbar-nav__right navbar-subscribe justify-content-center align-items-center"> <li class="nav-item"> <a class="nav-link" rel="noreferrer" href="https://twitter.com/paperswithcode"> <span class="nav-link-social-icon icon-wrapper icon-fa icon-fa-brands" data-name="twitter"><svg viewBox="0 0 512.001 515.25" xmlns="http://www.w3.org/2000/svg"><path d="M459.37 152.016c.326 4.548.326 9.097.326 13.645 0 138.72-105.583 298.558-298.559 298.558C101.685 464.22 46.457 447 0 417.114c8.447.973 16.568 1.298 25.34 1.298 49.054 0 94.213-16.568 130.274-44.832-46.132-.975-84.792-31.188-98.113-72.772 6.499.975 12.996 1.624 19.819 1.624 9.42 0 18.843-1.3 27.613-3.573-48.08-9.747-84.142-51.98-84.142-102.984v-1.3c13.968 7.798 30.213 12.67 47.43 13.32-28.263-18.843-46.78-51.006-46.78-87.391 0-19.492 5.196-37.36 14.294-52.954 51.654 63.674 129.3 105.258 216.364 109.807-1.624-7.797-2.599-15.918-2.599-24.04 0-57.827 46.782-104.934 104.934-104.934 30.214 0 57.502 12.67 76.671 33.136 23.715-4.548 46.455-13.319 66.599-25.34-7.798 24.367-24.366 44.834-46.132 57.828 21.117-2.274 41.584-8.122 60.426-16.244-14.292 20.791-32.161 39.309-52.628 54.253z"/></svg></span> </a> </li> <li class="nav-item"> <a id="signin-link" class="nav-link" href="/accounts/login?next=/sota/link-property-prediction-on-ogbl-ddi">Sign In</a> </li> </ul> </div> </nav>  <div class="modal fade" id="emailModal" tabindex="-1" role="dialog" aria-labelledby="emailModalLabel" aria-hidden="true"> <div class="modal-dialog" role="document"> <div class="modal-content"> <div class="modal-header"> <h3 class="modal-title" id="emailModalLabel">Subscribe to the PwC Newsletter</h3> <button type="button" class="close" data-dismiss="modal" data-bs-dismiss="modal" aria-label="Close"> <span aria-hidden="true">×</span> </button> </div> <form action="" method="post"> <div class="modal-body"> <div class="modal-body-info-text"> Stay informed on the latest trending ML papers with code, research developments, libraries, methods, and datasets.<br/><br/> <a href="/newsletter">Read previous issues</a> </div> <input type="hidden" name="csrfmiddlewaretoken" value="BYFVxdYwv0KYUM1RTsvHUkxijbyX2Kzv1OJ4uoSJrmho6JHhqWnHRJB5G2dOGmYL"> <input placeholder="Enter your email" type="email" class="form-control pwc-email" name="address" id="id_address" max_length="100" required> </div> <div class="modal-footer"> <button type="submit" class="btn btn-primary">Subscribe</button> </div> </form> </div> </div> </div>  <div class="modal fade" id="loginModal" tabindex="-1" role="dialog" aria-labelledby="loginModalLabel" aria-hidden="true"> <div class="modal-dialog" role="document"> <div class="modal-content"> <div class="modal-header"> <h5 class="modal-title" id="loginModalLabel">Join the community</h5> <button type="button" class="close btn-close" data-dismiss="modal" data-bs-dismiss="modal" aria-label="Close"> <span aria-hidden="true">×</span> </button> </div> <div class="login-modal-message"> You need to <a href="/accounts/login?next=/sota/link-property-prediction-on-ogbl-ddi">log in</a> to edit.<br/> You can <a href="/accounts/register?next=/sota/link-property-prediction-on-ogbl-ddi">create a new account</a> if you don't have one.<br/><br/> </div> </div> </div> </div> <div class="container content content-buffer "> <div class="leaderboard-header"> <a href="/task/link-property-prediction"> <span class="badge badge-primary"> <img src="https://production-media.paperswithcode.com/tasks/default.gif"> <span>Link Property Prediction</span> </span> </a> </div> <div id="sota-page"> <div class="text-center"> <img src="https://production-assets.paperswithcode.com/perf/images/spin-1s-32px-ed14c515.gif"> </div> </div> <link href="https://production-assets.paperswithcode.com/static/fonts/font-awesome/css/all.min.css" rel="stylesheet" /> <script type="application/javascript"> const CSRF_TOKEN = "BYFVxdYwv0KYUM1RTsvHUkxijbyX2Kzv1OJ4uoSJrmho6JHhqWnHRJB5G2dOGmYL"; const USER_IS_AUTHENTICATED = false; const LOGIN_REQUIRED = true; </script> <script type="module" src="https://unpkg.com/ionicons@5.1.2/dist/ionicons/ionicons.esm.js" ></script> <script nomodule="" src="https://unpkg.com/ionicons@5.1.2/dist/ionicons/ionicons.js" ></script>  <script id="evaluation-chart-data" type="application/json">{"all": {"yAxis": {"title": "Ext. data", "includeZero": false, "gridColor": "#ddd", "valueFormatString": ""}, "data": {"trend": {"name": "State-of-the-art methods", "type": "line", "showInLegend": true, "markerSize": 10, "toolTipContent": "{name}: {y}", "color": "#21ccc7", "dataPoints": []}, "other": {"name": "Other methods", "type": "scatter", "showInLegend": true, "color": "#ddd", "markerSize": 10, "toolTipContent": "{name}: {y}", "dataPoints": []}}}, "uses_additional_data": {"yAxis": {"title": "Ext. data", "includeZero": false, "gridColor": "#ddd", "valueFormatString": ""}, "data": {"trend": {"name": "State-of-the-art methods", "type": "line", "showInLegend": true, "markerSize": 10, "toolTipContent": "{name}: {y}", "color": "#21ccc7", "dataPoints": []}, "other": {"name": "Other methods", "type": "scatter", "showInLegend": true, "color": "#ddd", "markerSize": 10, "toolTipContent": "{name}: {y}", "dataPoints": []}}}, "no_additional_data": {"yAxis": {"title": "Ext. data", "includeZero": false, "gridColor": "#ddd", "valueFormatString": ""}, "data": {"trend": {"name": "State-of-the-art methods", "type": "line", "showInLegend": true, "markerSize": 10, "toolTipContent": "{name}: {y}", "color": "#21ccc7", "dataPoints": []}, "other": {"name": "Other methods", "type": "scatter", "showInLegend": true, "color": "#ddd", "markerSize": 10, "toolTipContent": "{name}: {y}", "dataPoints": []}}}}</script> <script id="evaluation-table-metrics" type="application/json">[{"id": 37406, "name": "Ext. data", "is_loss": false, "is_fixed": false}, {"id": 25370, "name": "Test Hits@20", "is_loss": false, "is_fixed": false}, {"id": 25371, "name": "Validation Hits@20", "is_loss": false, "is_fixed": false}, {"id": 26377, "name": "Number of params", "is_loss": false, "is_fixed": false}]</script> <script id="evaluation-table-data" type="application/json">[{"table_id": 10159, "row_id": 117054, "rank": 1, "method": "HyperFusion", "mlmodel": {}, "method_short": "HyperFusion", "method_details": null, "mlmodel_short": null, "mlmodeldetails": null, "evaluation_date": "2024-02-24", "metrics": {"Ext. data": "No", "Test Hits@20": "0.9972 \u00b1 0.0004", "Validation Hits@20": "0.9956 \u00b1 0.0001", "Number of params": "976022023"}, "raw_metrics": {"Ext. data": 0, "Test Hits@20": 0.9972, "Validation Hits@20": 0.9956, "Number of params": 976022023.0}, "uses_additional_data": false, "paper": {"id": null, "title": null, "url": null, "published": null, "code": false, "review_url": null}, "external_source_url": null, "tags": [], "reports": []}, {"table_id": 10159, "row_id": 111227, "rank": 2, "method": "ELGNN", "mlmodel": {}, "method_short": "ELGNN", "method_details": null, "mlmodel_short": null, "mlmodeldetails": null, "evaluation_date": "2023-10-22", "metrics": {"Ext. data": "No", "Test Hits@20": "0.9777 \u00b1 0.0037", "Validation Hits@20": "0.8965 \u00b1 0.0021", "Number of params": "10512391"}, "raw_metrics": {"Ext. data": 0, "Test Hits@20": 0.9777, "Validation Hits@20": 0.8965, "Number of params": 10512391.0}, "uses_additional_data": false, "paper": {"id": 1306085, "title": "Ensemble Learning for Graph Neural Networks", "url": "/paper/ensemble-learning-for-graph-neural-networks", "published": "2023-10-22T00:00:00.000000", "code": true, "review_url": "/paper/ensemble-learning-for-graph-neural-networks/review/?hl=111227"}, "external_source_url": null, "tags": [], "reports": []}, {"table_id": 10159, "row_id": 136150, "rank": 3, "method": "GCN (node embedding)", "mlmodel": {}, "method_short": "GCN ", "method_details": "node embedding", "mlmodel_short": null, "mlmodeldetails": null, "evaluation_date": "2024-11-22", "metrics": {"Ext. data": "No", "Test Hits@20": "0.9549 \u00b1 0.0073", "Validation Hits@20": "0.9098 \u00b1 0.0294", "Number of params": "5125250"}, "raw_metrics": {"Ext. data": 0, "Test Hits@20": 0.9549, "Validation Hits@20": 0.9098, "Number of params": 5125250.0}, "uses_additional_data": false, "paper": {"id": 1572378, "title": "Can GNNs Learn Link Heuristics? A Concise Review and Evaluation of Link Prediction Methods", "url": "/paper/can-gnns-learn-link-heuristics-a-concise", "published": "2024-11-22T00:00:00.000000", "code": true, "review_url": "/paper/can-gnns-learn-link-heuristics-a-concise/review/?hl=136150"}, "external_source_url": null, "tags": [], "reports": []}, {"table_id": 10159, "row_id": 71876, "rank": 4, "method": "GIDN@YITU", "mlmodel": {}, "method_short": "GIDN@YITU", "method_details": null, "mlmodel_short": null, "mlmodeldetails": null, "evaluation_date": "2022-10-04", "metrics": {"Ext. data": "No", "Test Hits@20": "0.9542 \u00b1 0.0000", "Validation Hits@20": "0.8258 \u00b1 0.0000", "Number of params": "3506691"}, "raw_metrics": {"Ext. data": 0, "Test Hits@20": 0.9542, "Validation Hits@20": 0.8258, "Number of params": 3506691.0}, "uses_additional_data": false, "paper": {"id": 1086394, "title": "GIDN: A Lightweight Graph Inception Diffusion Network for High-efficient Link Prediction", "url": "/paper/gidn-a-lightweight-graph-inception-diffusion", "published": "2022-10-04T00:00:00.000000", "code": false, "review_url": "/paper/gidn-a-lightweight-graph-inception-diffusion/review/?hl=71876"}, "external_source_url": null, "tags": [], "reports": []}, {"table_id": 10159, "row_id": 65376, "rank": 5, "method": "AGDN (AUC loss)", "mlmodel": {}, "method_short": "AGDN ", "method_details": "AUC loss", "mlmodel_short": null, "mlmodeldetails": null, "evaluation_date": "2020-12-30", "metrics": {"Ext. data": "No", "Test Hits@20": "0.9538 \u00b1 0.0094", "Validation Hits@20": "0.8943 \u00b1 0.0281", "Number of params": "3506691"}, "raw_metrics": {"Ext. data": 0, "Test Hits@20": 0.9538, "Validation Hits@20": 0.8943, "Number of params": 3506691.0}, "uses_additional_data": false, "paper": {"id": 732420, "title": "Adaptive Graph Diffusion Networks", "url": "/paper/adaptive-graph-diffusion-networks-with-hop", "published": "2020-12-30T00:00:00.000000", "code": true, "review_url": "/paper/adaptive-graph-diffusion-networks-with-hop/review/?hl=65376"}, "external_source_url": null, "tags": [], "reports": []}, {"table_id": 10159, "row_id": 136151, "rank": 6, "method": "Refined-GAE", "mlmodel": {}, "method_short": "Refined-GAE", "method_details": null, "mlmodel_short": null, "mlmodeldetails": null, "evaluation_date": "2024-11-06", "metrics": {"Ext. data": "No", "Test Hits@20": "0.9443 \u00b1 0.0057", "Validation Hits@20": "0.7979 \u00b1 0.0159", "Number of params": "13816833"}, "raw_metrics": {"Ext. data": 0, "Test Hits@20": 0.9443, "Validation Hits@20": 0.7979, "Number of params": 13816833.0}, "uses_additional_data": false, "paper": {"id": 1558875, "title": "Reconsidering the Performance of GAE in Link Prediction", "url": "/paper/reconsidering-the-performance-of-gae-in-link", "published": "2024-11-06T00:00:00.000000", "code": true, "review_url": "/paper/reconsidering-the-performance-of-gae-in-link/review/?hl=136151"}, "external_source_url": null, "tags": [], "reports": []}, {"table_id": 10159, "row_id": 63438, "rank": 7, "method": "PSG", "mlmodel": {}, "method_short": "PSG", "method_details": null, "mlmodel_short": null, "mlmodeldetails": null, "evaluation_date": "2022-08-10", "metrics": {"Ext. data": "No", "Test Hits@20": "0.9284 \u00b1 0.0047", "Validation Hits@20": "0.8306 \u00b1 0.0134", "Number of params": "3499009"}, "raw_metrics": {"Ext. data": 0, "Test Hits@20": 0.9284, "Validation Hits@20": 0.8306, "Number of params": 3499009.0}, "uses_additional_data": false, "paper": {"id": 1058023, "title": "Path-aware Siamese Graph Neural Network for Link Prediction", "url": "/paper/path-aware-siamese-graph-neural-network-for", "published": "2022-08-10T00:00:00.000000", "code": true, "review_url": "/paper/path-aware-siamese-graph-neural-network-for/review/?hl=63438"}, "external_source_url": null, "tags": [], "reports": []}, {"table_id": 10159, "row_id": 46146, "rank": 8, "method": "PLNLP", "mlmodel": {}, "method_short": "PLNLP", "method_details": null, "mlmodel_short": null, "mlmodeldetails": null, "evaluation_date": "2021-12-06", "metrics": {"Ext. data": "No", "Test Hits@20": "0.9088 \u00b1 0.0313", "Validation Hits@20": "0.8242 \u00b1 0.0253", "Number of params": "3497473"}, "raw_metrics": {"Ext. data": 0, "Test Hits@20": 0.9088, "Validation Hits@20": 0.8242, "Number of params": 3497473.0}, "uses_additional_data": false, "paper": {"id": 926084, "title": "Pairwise Learning for Neural Link Prediction", "url": "/paper/pairwise-learning-for-neural-link-prediction", "published": "2021-12-06T00:00:00.000000", "code": true, "review_url": "/paper/pairwise-learning-for-neural-link-prediction/review/?hl=46146"}, "external_source_url": null, "tags": [], "reports": []}, {"table_id": 10159, "row_id": 65377, "rank": 9, "method": "GDNN", "mlmodel": {}, "method_short": "GDNN", "method_details": null, "mlmodel_short": null, "mlmodeldetails": null, "evaluation_date": "2022-08-30", "metrics": {"Ext. data": "No", "Test Hits@20": "0.9037 \u00b1 0.0193", "Validation Hits@20": "0.8599 \u00b1 0.0286", "Number of params": "3761665"}, "raw_metrics": {"Ext. data": 0, "Test Hits@20": 0.9037, "Validation Hits@20": 0.8599, "Number of params": 3761665.0}, "uses_additional_data": false, "paper": {"id": null, "title": null, "url": null, "published": null, "code": false, "review_url": null}, "external_source_url": null, "tags": [], "reports": []}, {"table_id": 10159, "row_id": 38056, "rank": 10, "method": "GraphSAGE + Edge Attr", "mlmodel": {}, "method_short": "GraphSAGE + Edge Attr", "method_details": null, "mlmodel_short": null, "mlmodeldetails": null, "evaluation_date": "2021-08-09", "metrics": {"Ext. data": "No", "Test Hits@20": "0.8781 \u00b1 0.0474", "Validation Hits@20": "0.8044 \u00b1 0.0404", "Number of params": "3761665"}, "raw_metrics": {"Ext. data": 0, "Test Hits@20": 0.8781, "Validation Hits@20": 0.8044, "Number of params": 3761665.0}, "uses_additional_data": false, "paper": {"id": null, "title": null, "url": null, "published": null, "code": false, "review_url": null}, "external_source_url": null, "tags": [], "reports": []}, {"table_id": 10159, "row_id": 46147, "rank": 11, "method": "CFLP (w/ JKNet)", "mlmodel": {}, "method_short": "CFLP ", "method_details": "w/ JKNet", "mlmodel_short": null, "mlmodeldetails": null, "evaluation_date": "2021-06-03", "metrics": {"Ext. data": "No", "Test Hits@20": "0.8608 \u00b1 0.0198", "Validation Hits@20": "0.8405 \u00b1 0.0284", "Number of params": "837635"}, "raw_metrics": {"Ext. data": 0, "Test Hits@20": 0.8608, "Validation Hits@20": 0.8405, "Number of params": 837635.0}, "uses_additional_data": false, "paper": {"id": 811828, "title": "Learning from Counterfactual Links for Link Prediction", "url": "/paper/counterfactual-graph-learning-for-link", "published": "2021-06-03T00:00:00.000000", "code": true, "review_url": "/paper/counterfactual-graph-learning-for-link/review/?hl=46147"}, "external_source_url": null, "tags": [], "reports": []}, {"table_id": 10159, "row_id": 35355, "rank": 12, "method": "GraphSAGE+anchor distance", "mlmodel": {}, "method_short": "GraphSAGE+anchor distance", "method_details": null, "mlmodel_short": null, "mlmodeldetails": null, "evaluation_date": "2021-05-20", "metrics": {"Ext. data": "No", "Test Hits@20": "0.8239 \u00b1 0.0437", "Validation Hits@20": "0.8206 \u00b1 0.0298", "Number of params": "3760134"}, "raw_metrics": {"Ext. data": 0, "Test Hits@20": 0.8239, "Validation Hits@20": 0.8206, "Number of params": 3760134.0}, "uses_additional_data": false, "paper": {"id": 821674, "title": "Distance-Enhanced Graph Neural Network for Link Prediction", "url": "/paper/distance-enhanced-graph-neural-network-for", "published": "2021-05-20T00:00:00.000000", "code": true, "review_url": null}, "external_source_url": null, "tags": [], "reports": []}, {"table_id": 10159, "row_id": 100331, "rank": 13, "method": "NeuralCommonNeighbor", "mlmodel": {}, "method_short": "NeuralCommonNeighbor", "method_details": null, "mlmodel_short": null, "mlmodeldetails": null, "evaluation_date": "2023-02-02", "metrics": {"Ext. data": "No", "Test Hits@20": "0.8232 \u00b1 0.0610", "Validation Hits@20": "0.7172 \u00b1 0.0025", "Number of params": "1412098"}, "raw_metrics": {"Ext. data": 0, "Test Hits@20": 0.8232, "Validation Hits@20": 0.7172, "Number of params": 1412098.0}, "uses_additional_data": false, "paper": {"id": 1151670, "title": "Neural Common Neighbor with Completion for Link Prediction", "url": "/paper/neural-common-neighbor-with-completion-for", "published": "2023-02-02T00:00:00.000000", "code": true, "review_url": "/paper/neural-common-neighbor-with-completion-for/review/?hl=100331"}, "external_source_url": null, "tags": [], "reports": []}, {"table_id": 10159, "row_id": 105764, "rank": 14, "method": "ELPH", "mlmodel": {}, "method_short": "ELPH", "method_details": null, "mlmodel_short": null, "mlmodeldetails": null, "evaluation_date": "2023-07-05", "metrics": {"Ext. data": "No", "Test Hits@20": "0.7704 \u00b1 0.0582", "Validation Hits@20": "0.6928 \u00b1 0.0096", "Number of params": "2910817"}, "raw_metrics": {"Ext. data": 0, "Test Hits@20": 0.7704, "Validation Hits@20": 0.6928, "Number of params": 2910817.0}, "uses_additional_data": false, "paper": {"id": null, "title": null, "url": null, "published": null, "code": false, "review_url": null}, "external_source_url": null, "tags": [], "reports": []}, {"table_id": 10159, "row_id": 36058, "rank": 15, "method": "DEA + JKNet", "mlmodel": {}, "method_short": "DEA + JKNet", "method_details": null, "mlmodel_short": null, "mlmodeldetails": null, "evaluation_date": "2021-03-21", "metrics": {"Ext. data": "No", "Test Hits@20": "0.7672 \u00b1 0.0265", "Validation Hits@20": "0.6713 \u00b1 0.0071", "Number of params": "1763329"}, "raw_metrics": {"Ext. data": 0, "Test Hits@20": 0.7672, "Validation Hits@20": 0.6713, "Number of params": 1763329.0}, "uses_additional_data": false, "paper": {"id": null, "title": null, "url": null, "published": null, "code": false, "review_url": null}, "external_source_url": null, "tags": [], "reports": []}, {"table_id": 10159, "row_id": 105765, "rank": 16, "method": "BUDDY", "mlmodel": {}, "method_short": "BUDDY", "method_details": null, "mlmodel_short": null, "mlmodeldetails": null, "evaluation_date": "2023-07-04", "metrics": {"Ext. data": "No", "Test Hits@20": "0.7654 \u00b1 0.0459", "Validation Hits@20": "0.6927 \u00b1 0.0054", "Number of params": "2712931"}, "raw_metrics": {"Ext. data": 0, "Test Hits@20": 0.7654, "Validation Hits@20": 0.6927, "Number of params": 2712931.0}, "uses_additional_data": false, "paper": {"id": null, "title": null, "url": null, "published": null, "code": false, "review_url": null}, "external_source_url": null, "tags": [], "reports": []}, {"table_id": 10159, "row_id": 37470, "rank": 17, "method": "GraphSAGE+Edge Proposal Set", "mlmodel": {}, "method_short": "GraphSAGE+Edge Proposal Set", "method_details": null, "mlmodel_short": null, "mlmodeldetails": null, "evaluation_date": "2021-06-30", "metrics": {"Ext. data": "No", "Test Hits@20": "0.7495 \u00b1 0.0317", "Validation Hits@20": "0.6696 \u00b1 0.0198", "Number of params": "1421057"}, "raw_metrics": {"Ext. data": 0, "Test Hits@20": 0.7495, "Validation Hits@20": 0.6696, "Number of params": 1421057.0}, "uses_additional_data": false, "paper": {"id": 827602, "title": "Edge Proposal Sets for Link Prediction", "url": "/paper/edge-proposal-sets-for-link-prediction", "published": "2021-06-30T00:00:00.000000", "code": true, "review_url": "/paper/edge-proposal-sets-for-link-prediction/review/?hl=37470"}, "external_source_url": null, "tags": [], "reports": []}, {"table_id": 10159, "row_id": 36059, "rank": 18, "method": "LRGA+GCN(Node2Vec+Augment)", "mlmodel": {}, "method_short": "LRGA+GCN", "method_details": "Node2Vec+Augment", "mlmodel_short": null, "mlmodeldetails": null, "evaluation_date": "2021-03-21", "metrics": {"Ext. data": "No", "Test Hits@20": "0.7385 \u00b1 0.0871", "Validation Hits@20": "0.7225 \u00b1 0.0047", "Number of params": "10235281"}, "raw_metrics": {"Ext. data": 0, "Test Hits@20": 0.7385, "Validation Hits@20": 0.7225, "Number of params": 10235281.0}, "uses_additional_data": false, "paper": {"id": null, "title": null, "url": null, "published": null, "code": false, "review_url": null}, "external_source_url": null, "tags": [], "reports": []}, {"table_id": 10159, "row_id": 36060, "rank": 19, "method": "MAD Learning", "mlmodel": {}, "method_short": "MAD Learning", "method_details": null, "mlmodel_short": null, "mlmodeldetails": null, "evaluation_date": "2021-02-10", "metrics": {"Ext. data": "No", "Test Hits@20": "0.6781 \u00b1 0.0294", "Validation Hits@20": "0.7010 \u00b1 0.0082", "Number of params": "1228897"}, "raw_metrics": {"Ext. data": 0, "Test Hits@20": 0.6781, "Validation Hits@20": 0.701, "Number of params": 1228897.0}, "uses_additional_data": false, "paper": {"id": 744038, "title": "Memory-Associated Differential Learning", "url": "/paper/memory-associated-differential-learning", "published": "2021-02-10T00:00:00.000000", "code": true, "review_url": "/paper/memory-associated-differential-learning/review/?hl=36060"}, "external_source_url": null, "tags": [], "reports": []}, {"table_id": 10159, "row_id": 36061, "rank": 20, "method": "LRGA + GCN", "mlmodel": {}, "method_short": "LRGA + GCN", "method_details": null, "mlmodel_short": null, "mlmodeldetails": null, "evaluation_date": "2020-06-14", "metrics": {"Ext. data": "No", "Test Hits@20": "0.6230 \u00b1 0.0912", "Validation Hits@20": "0.6675 \u00b1 0.0058", "Number of params": "1576081"}, "raw_metrics": {"Ext. data": 0, "Test Hits@20": 0.623, "Validation Hits@20": 0.6675, "Number of params": 1576081.0}, "uses_additional_data": false, "paper": {"id": 202387, "title": "Global Attention Improves Graph Networks Generalization", "url": "/paper/from-graph-low-rank-global-attention-to-2-fwl", "published": "2020-06-14T00:00:00.000000", "code": true, "review_url": "/paper/from-graph-low-rank-global-attention-to-2-fwl/review/?hl=36061"}, "external_source_url": null, "tags": [], "reports": []}, {"table_id": 10159, "row_id": 70979, "rank": 21, "method": "GCN+JKNet", "mlmodel": {}, "method_short": "GCN+JKNet", "method_details": null, "mlmodel_short": null, "mlmodeldetails": null, "evaluation_date": "2016-09-09", "metrics": {"Ext. data": "No", "Test Hits@20": "0.6056 \u00b1 0.0869", "Validation Hits@20": "0.6776 \u00b1 0.0095", "Number of params": "1421571"}, "raw_metrics": {"Ext. data": 0, "Test Hits@20": 0.6056, "Validation Hits@20": 0.6776, "Number of params": 1421571.0}, "uses_additional_data": false, "paper": {"id": 26050, "title": "Semi-Supervised Classification with Graph Convolutional Networks", "url": "/paper/semi-supervised-classification-with-graph", "published": "2016-09-09T00:00:00.000000", "code": true, "review_url": "/paper/semi-supervised-classification-with-graph/review/?hl=70979"}, "external_source_url": null, "tags": [], "reports": []}, {"table_id": 10159, "row_id": 63794, "rank": 22, "method": "NGNN + GraphSAGE", "mlmodel": {}, "method_short": "NGNN + GraphSAGE", "method_details": null, "mlmodel_short": null, "mlmodeldetails": null, "evaluation_date": "2021-11-23", "metrics": {"Ext. data": "No", "Test Hits@20": "0.5770 \u00b1 0.1523", "Validation Hits@20": "0.7323 \u00b1 0.0040", "Number of params": "1618433"}, "raw_metrics": {"Ext. data": 0, "Test Hits@20": 0.577, "Validation Hits@20": 0.7323, "Number of params": 1618433.0}, "uses_additional_data": false, "paper": {"id": 915506, "title": "Network In Graph Neural Network", "url": "/paper/network-in-graph-neural-network", "published": "2021-11-23T00:00:00.000000", "code": false, "review_url": "/paper/network-in-graph-neural-network/review/?hl=63794"}, "external_source_url": null, "tags": [], "reports": []}, {"table_id": 10159, "row_id": 63795, "rank": 23, "method": "NGNN + GCN", "mlmodel": {}, "method_short": "NGNN + GCN", "method_details": null, "mlmodel_short": null, "mlmodeldetails": null, "evaluation_date": "2021-11-23", "metrics": {"Ext. data": "No", "Test Hits@20": "0.5483 \u00b1 0.1581", "Validation Hits@20": "0.7121 \u00b1 0.0038", "Number of params": "1487361"}, "raw_metrics": {"Ext. data": 0, "Test Hits@20": 0.5483, "Validation Hits@20": 0.7121, "Number of params": 1487361.0}, "uses_additional_data": false, "paper": {"id": 915506, "title": "Network In Graph Neural Network", "url": "/paper/network-in-graph-neural-network", "published": "2021-11-23T00:00:00.000000", "code": false, "review_url": "/paper/network-in-graph-neural-network/review/?hl=63795"}, "external_source_url": null, "tags": [], "reports": []}, {"table_id": 10159, "row_id": 36063, "rank": 24, "method": "GraphSAGE", "mlmodel": {}, "method_short": "GraphSAGE", "method_details": null, "mlmodel_short": null, "mlmodeldetails": null, "evaluation_date": "2017-06-07", "metrics": {"Ext. data": "No", "Test Hits@20": "0.5390 \u00b1 0.0474", "Validation Hits@20": "0.6262 \u00b1 0.0037", "Number of params": "1421057"}, "raw_metrics": {"Ext. data": 0, "Test Hits@20": 0.539, "Validation Hits@20": 0.6262, "Number of params": 1421057.0}, "uses_additional_data": false, "paper": {"id": 6336, "title": "Inductive Representation Learning on Large Graphs", "url": "/paper/inductive-representation-learning-on-large", "published": "2017-06-07T00:00:00.000000", "code": true, "review_url": "/paper/inductive-representation-learning-on-large/review/?hl=36063"}, "external_source_url": null, "tags": [], "reports": []}, {"table_id": 10159, "row_id": 70980, "rank": 25, "method": "GCN", "mlmodel": {}, "method_short": "GCN", "method_details": null, "mlmodel_short": null, "mlmodeldetails": null, "evaluation_date": "2016-09-09", "metrics": {"Ext. data": "No", "Test Hits@20": "0.3707 \u00b1 0.0507", "Validation Hits@20": "0.5550 \u00b1 0.0208", "Number of params": "1289985"}, "raw_metrics": {"Ext. data": 0, "Test Hits@20": 0.3707, "Validation Hits@20": 0.555, "Number of params": 1289985.0}, "uses_additional_data": false, "paper": {"id": 26050, "title": "Semi-Supervised Classification with Graph Convolutional Networks", "url": "/paper/semi-supervised-classification-with-graph", "published": "2016-09-09T00:00:00.000000", "code": true, "review_url": "/paper/semi-supervised-classification-with-graph/review/?hl=70980"}, "external_source_url": null, "tags": [], "reports": []}, {"table_id": 10159, "row_id": 36065, "rank": 26, "method": "SEAL", "mlmodel": {}, "method_short": "SEAL", "method_details": null, "mlmodel_short": null, "mlmodeldetails": null, "evaluation_date": "2020-10-30", "metrics": {"Ext. data": "No", "Test Hits@20": "0.3056 \u00b1 0.0386", "Validation Hits@20": "0.2849 \u00b1 0.0269", "Number of params": "531138"}, "raw_metrics": {"Ext. data": 0, "Test Hits@20": 0.3056, "Validation Hits@20": 0.2849, "Number of params": 531138.0}, "uses_additional_data": false, "paper": {"id": 231874, "title": "Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning", "url": "/paper/revisiting-graph-neural-networks-for-link-1", "published": "2020-10-30T00:00:00.000000", "code": true, "review_url": "/paper/revisiting-graph-neural-networks-for-link-1/review/?hl=36065"}, "external_source_url": null, "tags": [], "reports": []}, {"table_id": 10159, "row_id": 36067, "rank": 27, "method": "Node2vec", "mlmodel": {}, "method_short": "Node2vec", "method_details": null, "mlmodel_short": null, "mlmodeldetails": null, "evaluation_date": "2016-07-03", "metrics": {"Ext. data": "No", "Test Hits@20": "0.2326 \u00b1 0.0209", "Validation Hits@20": "0.3292 \u00b1 0.0121", "Number of params": "645249"}, "raw_metrics": {"Ext. data": 0, "Test Hits@20": 0.2326, "Validation Hits@20": 0.3292, "Number of params": 645249.0}, "uses_additional_data": false, "paper": {"id": 32464, "title": "node2vec: Scalable Feature Learning for Networks", "url": "/paper/node2vec-scalable-feature-learning-for", "published": "2016-07-03T00:00:00.000000", "code": true, "review_url": "/paper/node2vec-scalable-feature-learning-for/review/?hl=36067"}, "external_source_url": null, "tags": [], "reports": []}, {"table_id": 10159, "row_id": 36066, "rank": 28, "method": "DeepWalk", "mlmodel": {}, "method_short": "DeepWalk", "method_details": null, "mlmodel_short": null, "mlmodeldetails": null, "evaluation_date": "2014-03-26", "metrics": {"Ext. data": "No", "Test Hits@20": "0.2246 \u00b1 0.0290", "Validation Hits@20": "Please tell us", "Number of params": "1543913"}, "raw_metrics": {"Ext. data": 0, "Test Hits@20": 0.2246, "Validation Hits@20": 0, "Number of params": 1543913.0}, "uses_additional_data": false, "paper": {"id": 44902, "title": "DeepWalk: Online Learning of Social Representations", "url": "/paper/deepwalk-online-learning-of-social", "published": "2014-03-26T00:00:00.000000", "code": true, "review_url": null}, "external_source_url": null, "tags": [], "reports": []}, {"table_id": 10159, "row_id": 36068, "rank": 29, "method": "Adamic Adar", "mlmodel": {}, "method_short": "Adamic Adar", "method_details": null, "mlmodel_short": null, "mlmodeldetails": null, "evaluation_date": "2021-02-12", "metrics": {"Ext. data": "No", "Test Hits@20": "0.1861 \u00b1 0.0000", "Validation Hits@20": "0.0966 \u00b1 0.0000", "Number of params": "0"}, "raw_metrics": {"Ext. data": 0, "Test Hits@20": 0.1861, "Validation Hits@20": 0.0966, "Number of params": 0.0}, "uses_additional_data": false, "paper": {"id": null, "title": null, "url": null, "published": null, "code": false, "review_url": null}, "external_source_url": null, "tags": [], "reports": []}, {"table_id": 10159, "row_id": 36069, "rank": 30, "method": "Common Neighbor", "mlmodel": {}, "method_short": "Common Neighbor", "method_details": null, "mlmodel_short": null, "mlmodeldetails": null, "evaluation_date": "2021-02-12", "metrics": {"Ext. data": "No", "Test Hits@20": "0.1773 \u00b1 0.0000", "Validation Hits@20": "0.0947 \u00b1 0.0000", "Number of params": "0"}, "raw_metrics": {"Ext. data": 0, "Test Hits@20": 0.1773, "Validation Hits@20": 0.0947, "Number of params": 0.0}, "uses_additional_data": false, "paper": {"id": null, "title": null, "url": null, "published": null, "code": false, "review_url": null}, "external_source_url": null, "tags": [], "reports": []}, {"table_id": 10159, "row_id": 36070, "rank": 31, "method": "Matrix Factorization", "mlmodel": {}, "method_short": "Matrix Factorization", "method_details": null, "mlmodel_short": null, "mlmodeldetails": null, "evaluation_date": "2020-05-02", "metrics": {"Ext. data": "No", "Test Hits@20": "0.1368 \u00b1 0.0475", "Validation Hits@20": "0.3370 \u00b1 0.0264", "Number of params": "1224193"}, "raw_metrics": {"Ext. data": 0, "Test Hits@20": 0.1368, "Validation Hits@20": 0.337, "Number of params": 1224193.0}, "uses_additional_data": false, "paper": {"id": 193610, "title": "Open Graph Benchmark: Datasets for Machine Learning on Graphs", "url": "/paper/open-graph-benchmark-datasets-for-machine", "published": "2020-05-02T00:00:00.000000", "code": true, "review_url": "/paper/open-graph-benchmark-datasets-for-machine/review/?hl=36070"}, "external_source_url": null, "tags": [], "reports": []}]</script> <script id="community-chart-data" type="application/json">{"all": {"yAxis": {"title": "Ext. data", "includeZero": false, "gridColor": "#ddd", "valueFormatString": ""}, "data": {"trend": {"name": "State-of-the-art methods", "type": "line", "showInLegend": true, "markerSize": 10, "toolTipContent": "{name}: {y}", "color": "#21ccc7", "dataPoints": []}, "other": {"name": "Other methods", "type": "scatter", "showInLegend": true, "color": "#ddd", "markerSize": 10, "toolTipContent": "{name}: {y}", "dataPoints": []}}}, "uses_additional_data": {"yAxis": {"title": "Ext. data", "includeZero": false, "gridColor": "#ddd", "valueFormatString": ""}, "data": {"trend": {"name": "State-of-the-art methods", "type": "line", "showInLegend": true, "markerSize": 10, "toolTipContent": "{name}: {y}", "color": "#21ccc7", "dataPoints": []}, "other": {"name": "Other methods", "type": "scatter", "showInLegend": true, "color": "#ddd", "markerSize": 10, "toolTipContent": "{name}: {y}", "dataPoints": []}}}, "no_additional_data": {"yAxis": {"title": "Ext. data", "includeZero": false, "gridColor": "#ddd", "valueFormatString": ""}, "data": {"trend": {"name": "State-of-the-art methods", "type": "line", "showInLegend": true, "markerSize": 10, "toolTipContent": "{name}: {y}", "color": "#21ccc7", "dataPoints": []}, "other": {"name": "Other methods", "type": "scatter", "showInLegend": true, "color": "#ddd", "markerSize": 10, "toolTipContent": "{name}: {y}", "dataPoints": []}}}}</script> <script id="community-table-metrics" type="application/json">[]</script> <script id="community-table-data" type="application/json">[]</script> <script id="dataset-details" type="application/json">[{"name": "OGB", "fullName": "Open Graph Benchmark", "url": "/dataset/ogb", "description": "The Open Graph Benchmark (OGB) is a collection of realistic, large-scale, and diverse benchmark datasets for machine learning on graphs. OGB datasets are automatically downloaded, processed, and split using the OGB Data Loader. The model performance can be evaluated using the OGB Evaluator in a unified manner.\nOGB is a community-driven initiative in active development.", "imagePath": "https://production-media.paperswithcode.com/datasets/OGB-0000005008-7c47e954.jpg", "iconName": "draw-polygon", "color": "#90B06D"}]</script> <script id="sota-page-details" type="application/json">{"task_main_area_name": "Graphs", "task_name": "Link Property Prediction", "dataset_name": "ogbl-ddi", "description": "This page is mirroring [Link Property Prediction LeaderBoard](https://ogb.stanford.edu/docs/leader_linkprop/).", "mirror_url": null, "has_competition_entries": false}</script> <script type="application/javascript"> let evaluationChartData = JSON.parse( document.getElementById("evaluation-chart-data").textContent ); let evaluationTableMetrics = JSON.parse( document.getElementById("evaluation-table-metrics").textContent ); let evaluationTableData = JSON.parse( document.getElementById("evaluation-table-data").textContent ); let communityChartData = JSON.parse( document.getElementById("community-chart-data").textContent ); let communityTableMetrics = JSON.parse( document.getElementById("community-table-metrics").textContent ); let communityTableData = JSON.parse( document.getElementById("community-table-data").textContent ); let datasetDetails = JSON.parse( document.getElementById("dataset-details").textContent ); let sotaPageDetails = JSON.parse( document.getElementById("sota-page-details").textContent ); // Containers let sotaPageContainer = document.getElementById("sota-page"); // Breadcrumbs let breadcrumbs = [ { title: "Browse", url: "/sota" }, { title: sotaPageDetails.task_main_area_name, url: "/area/graphs" }, { title: sotaPageDetails.task_name, url: "/task/link-property-prediction" }, { title: sotaPageDetails.dataset_name + " dataset", url: "/dataset/ogb" } ]; let highlight = ( null ); function datasetsSearchUrl(query) { return "/datasets?q="+encodeURIComponent(query); } function newDatasetUrl(datasetName) { return "/contribute/dataset/new?name="+encodeURIComponent(datasetName); } const SOTA_AUTOCOMPLETE_PAPER_URL = "/sota/autocomplete/paper"; const VIEW_PAPER_URL = "/paper/PAPER_SLUG"; </script>  </div> <div class="footer"> <div class="footer-contact"> <span class="footer-contact-item">Contact us on:</span> <a class="footer-contact-item" href="mailto:hello@paperswithcode.com"> <span class=" icon-wrapper icon-ion" data-name="mail"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M424 80H88a56.06 56.06 0 0 0-56 56v240a56.06 56.06 0 0 0 56 56h336a56.06 56.06 0 0 0 56-56V136a56.06 56.06 0 0 0-56-56zm-14.18 92.63l-144 112a16 16 0 0 1-19.64 0l-144-112a16 16 0 1 1 19.64-25.26L256 251.73l134.18-104.36a16 16 0 0 1 19.64 25.26z"/></svg></span> hello@paperswithcode.com </a>. <span class="footer-contact-item"> Papers With Code is a free resource with all data licensed under <a rel="noreferrer" href="https://creativecommons.org/licenses/by-sa/4.0/">CC-BY-SA</a>. </span> </div> <div class="footer-links"> <a href="/site/terms">Terms</a> <a href="/site/data-policy">Data policy</a> <a href="/site/cookies-policy">Cookies policy</a> <a href="/about#team" class="fair-logo"> from <img src="data:image/png;base64,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"> </a> </div> </div> <script> // MathJax window.MathJax = { tex: { inlineMath: [ ["$", "$"], ["\$", "\$"], ], }, }; const mathjaxScript = document.createElement("script"); mathjaxScript.src = "https://production-assets.paperswithcode.com/static/js/mathjax/tex-chtml.js"; document.head.appendChild(mathjaxScript); </script> <script src="https://production-assets.paperswithcode.com/perf/766.4af6b88b.js" defer></script><script src="https://production-assets.paperswithcode.com/perf/2.6da00df7.js" defer></script><script src="https://production-assets.paperswithcode.com/perf/351.a22a9607.js" defer></script><script src="https://production-assets.paperswithcode.com/perf/452.d3ecdfa4.js" defer></script><script src="https://production-assets.paperswithcode.com/perf/553.357efc0e.js" defer></script><script src="https://production-assets.paperswithcode.com/perf/sota.table.040f2c99.js" defer></script> </body> </html>