<div dir="ltr"><div class="gmail_quote"><div class="msg-3859891249619387508"><div lang="EN-US" link="#0563C1" vlink="#954F72" style="word-wrap:break-word"><div class="m_-942489863848093100WordSection1"><h2 style="line-height:20.5pt;vertical-align:baseline"><span style="font-size:16.0pt;font-family:"Museo Slab 300";color:#4d4d4d;letter-spacing:.1pt;font-weight:normal">Foundations of Data Science Seminar Series<u></u><u></u></span></h2>
<p class="MsoNormal" style="line-height:15.1pt;vertical-align:baseline;margin:0.75rem;outline:0px;font-variant:inherit;font-stretch:inherit;font-size:0.9rem;letter-spacing:0.01rem">
<span class="m_-942489863848093100date-display-single"><span style="font-family:"Open Sans",sans-serif;color:#003d75;letter-spacing:.1pt;border:none windowtext 1.0pt;padding:0in">Wednesday, October 5, 2022 - 4:00pm</span></span><span style="font-size:11.0pt;font-family:"Open Sans",sans-serif;color:#4d4d4d;letter-spacing:.1pt"><u></u><u></u></span></p>
<p style="line-height:15.1pt;vertical-align:baseline"><strong><span style="font-family:inherit;color:#003d75;letter-spacing:.1pt;border:none windowtext 1.0pt;padding:0in">Speaker: Rex Ying</span></strong><span style="font-family:"Open Sans",sans-serif;color:#4d4d4d;letter-spacing:.1pt"><br>
Assistant Professor of Computer Science<u></u><u></u></span></p>
<h2 style="line-height:20.5pt;vertical-align:baseline;margin:0.75rem;outline:0px;font-variant:inherit;font-stretch:inherit;letter-spacing:0.01rem">
<strong><i><span style="font-size:16.0pt;font-family:inherit;color:#003d75;letter-spacing:.1pt;border:none windowtext 1.0pt;padding:0in">“Graph Representation Learning: A Geometric Perspective”<u></u><u></u></span></i></strong></h2>
<p class="MsoNormal" style="line-height:15.1pt;vertical-align:baseline"><b><span style="font-size:11.0pt;color:#4d4d4d;letter-spacing:.1pt">Location: </span></b><span class="m_-942489863848093100fn"><span style="font-size:11.0pt;color:#4d4d4d;letter-spacing:.1pt;border:none windowtext 1.0pt;padding:0in">DL220</span></span><b><span style="font-size:11.0pt;color:#4d4d4d;letter-spacing:.1pt"><u></u><u></u></span></b></p>
<p class="MsoNormal" style="line-height:15.1pt;vertical-align:baseline"><span style="font-size:11.0pt;color:#4d4d4d;letter-spacing:.1pt">10 Hillhouse Avenue</span><span style="color:#4d4d4d;letter-spacing:.1pt">,
</span><span class="m_-942489863848093100locality"><span style="font-size:11.0pt;color:#4d4d4d;letter-spacing:.1pt;border:none windowtext 1.0pt;padding:0in">New Haven</span></span><span style="font-size:11.0pt;color:#4d4d4d;letter-spacing:.1pt">, <span class="m_-942489863848093100region"><span style="border:none windowtext 1.0pt;padding:0in">CT</span><u></u><u></u></span></span></p>
<p class="MsoNormal" style="line-height:15.1pt;vertical-align:baseline"><span class="m_-942489863848093100region"><span style="font-size:11.0pt;color:#4d4d4d;letter-spacing:.1pt;border:none windowtext 1.0pt;padding:0in"><u></u> <u></u></span></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt">In-person talk, but remote access available here:
<a href="https://yale.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=54684a12-8f27-4506-a30d-af1c0126145d" target="_blank">
https://yale.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=54684a12-8f27-4506-a30d-af1c0126145d</a><u></u><u></u></span></p>
<p style="line-height:15.1pt;vertical-align:baseline"><strong><span style="font-family:"Calibri",sans-serif;color:#003d75;letter-spacing:.1pt;border:none windowtext 1.0pt;padding:0in">Abstract:</span></strong><span style="color:#4d4d4d;letter-spacing:.1pt"> The
 talk focuses on geometric embedding approaches to representation learning on graph-structured data. We observe that certain inductive biases of graph data, such as hierarchies and transitive closures, can be modeled more effectively through different embedding
 geometries. We leverage hyperbolic embeddings, cone embeddings and order embeddings for incorporating these inductive biases of input graph data when learning node and graph representations for large-scale, heterogeneous graph data and challenging tasks.<u></u><u></u></span></p>
<p style="line-height:15.1pt;vertical-align:baseline;margin:0.75rem;outline:0px;font-variant:inherit;font-stretch:inherit;font-size:0.9rem;letter-spacing:0.01rem">
<strong><span style="font-family:"Calibri",sans-serif;color:#003d75;letter-spacing:.1pt;border:none windowtext 1.0pt;padding:0in">Speaker Bio:</span></strong><span style="color:#4d4d4d;letter-spacing:.1pt">  Rex Ying is an assistant professor in the Department
 of Computer Science at Yale University. His research focus includes algorithms for graph neural networks, geometric embeddings, and trustworthy ML on graphs. He is the author of many widely used GNN algorithms such as GraphSAGE, PinSAGE and GNNExplainer. In
 addition, Rex worked on a variety of applications of graph learning in physical simulations, social networks, NLP, knowledge graphs and biology. He developed the first billion-scale graph embedding services at Pinterest, and the graph-based anomaly detection
 algorithm at Amazon. He is the winner of the dissertation award at KDD 2022.<u></u><u></u></span></p>
<p class="MsoNormal"><a href="https://yale.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=7e3a4115-73f7-4205-976d-af1c01266047" target="_blank">Next week: 10/12@4pm Smita Krishnaswamy</a><u></u><u></u></p>
<p class="MsoNormal"><span style="font-size:11.0pt"><u></u> <u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt"><u></u> <u></u></span></p>
<div>
<div>
<div>
<p class="MsoNormal"><span style="color:black">Emily E. H. Hau | Associate Director, Data Science @ Yale University<u></u><u></u></span></p>
<p class="MsoNormal"><b><i><span style="color:#4472c4">Yale Institute for Foundations of Data Science (FDS)</span></i></b><span style="color:black"><u></u><u></u></span></p>
<p class="MsoNormal"><b><i><span style="color:#4472c4">Yale Institute for Network Science (YINS)</span></i></b><span style="color:black"><u></u><u></u></span></p>
<p class="MsoNormal"><span style="color:black">17 Hillhouse Avenue | Room 341 | New Haven, CT 06511<u></u><u></u></span></p>
<p class="MsoNormal"><u><span lang="PT-BR" style="color:#0563c1"><a href="mailto:emily.hau@yale.edu" title="mailto:emily.hau@yale.edu" target="_blank"><span style="color:#0563c1">emily.hau@yale.edu</span></a> | </span></u><span lang="PT-BR" style="color:black">P: 203-436-4732 </span><span style="color:black"><u></u><u></u></span></p>
<p class="MsoNormal"><span style="color:black">@yaledatascience @YINSedge @EmilyDeeganHau<u></u><u></u></span></p>
</div>
</div>
</div>
<p class="MsoNormal"><span style="font-size:11.0pt"><u></u> <u></u></span></p>
<div>
<p class="MsoNormal"><span style="font-size:11.0pt"><u></u> <u></u></span></p>
</div>
</div>
</div>

</div></div></div>