Research Seminar by Rex YING | Towards relation-aware foundation models

Recent years have seen tremendous progress in modeling graph-structured data through deep learning, transforming models’ ability to understand relational structure. In this talk I will demonstrate explorations that leverage graph structure to empower complex and efficient reasoning in various machine learning scenarios, focusing on the use in foundation models. The works aim to ultimately develop generic pre-trained graph encoding architecture for structured data that can be applied to any use cases through multimodal integration. 

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, explainable models, and more recently, foundation models and multi-modal models involving relational reasoning. Rex is the author of many widely used GNN algorithms such as GraphSAGE, PinSAGE and GNNExplainer. In addition, Rex has worked on a variety of applications of graph learning in physics, biomedicine, social networks, knowledge graphs and neuroscience. His research has been supported by National Science Foundation, Amazon Web Services and Snap Inc.