<div dir="ltr">Rex Ying (Yale CS) will be speaking on Wednesday at 4pm in DL220.<div><br></div><div>The title of his talk is "Graph Representation Learning: A Geometric Perspective"</div><div><br></div><div>Abstract:</div>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.<br><div><br></div><div>More info, including the link to stream the talk, can be found at:</div><div><a href="https://yins.yale.edu/event/fds-seminar-rex-ying">https://yins.yale.edu/event/fds-seminar-rex-ying</a><br></div><div><br></div><div><br></div></div>