ABSTRACT:

Recent years have seen tremendous progress in modeling graph-structured data through deep networks, transforming models’ ability to understand relational structure. A natural question is: how could we leverage such progress on data that do not directly manifest as graph structure? This talk focuses on 3 aspects that show promises in this direction: graph structure learning, heterogeneous relation construction and attention diffusion. Diverse applications in language models, AutoML, and algorithmic reasoning have demonstrated the effectiveness of deep graph representation learning in a much broader context, through identifying the right relations for GNN models to reason on.

Bio:

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. 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.

Hosted by Professor Baharan Mirzasoleiman