Invited talk by Cris Bodnar

Zoom link:

Invited talk by Cris Bodnar (University of Cambridge).

This week’s talk on “Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs”, will be given by Cris Bodnar, a doctoral student at the Computer Laboratory.

Cris uses applied Topology and Differential Geometry for understanding and developing Geometric Deep Learning models suitable for problems presenting an underlying combinatorial structure. Within this area, he is particularly interested in theoretical questions of practical importance for graph representation learning. Cris was awarded the Microsoft Research PhD Fellowship in 2021.