Friday, 27th October - 11am Christopher Morris : Seminar

Title: Weisfeiler and Leman Go Machine Learning: Expressivity and Generalization of Graph Neural Networks

Abstract:

Graph-structured data is prevalent across various domains, such as chemo-and bioinformatics, image analysis, and social network analysis. As a result, there has been a surge in the development of machine-learning methods explicitly tailored to graphs. Among these methods, (message-passing) graph neural networks (GNNs) have emerged as the dominant paradigm. Despite their practical success, GNNs' capabilities and limitations are understood to a lesser extent. In this talk, we survey results connecting GNNs' expressive power and generalization abilities to a simple heuristic for the graph isomorphism problem---the Weisfeiler-Leman algorithm.

 vCal  iCal