Michael Bronstein | Neural diffusion PDEs, differential geometry, and graph neural networks

2/2/2022 CMSA New Technologies in Mathematics Seminar Speaker: Michael Bronstein, University of Oxford and Twitter Title: Neural diffusion PDEs, differential geometry, and graph neural networks Abstract: In this talk, I will make connections between Graph Neural Networks (GNNs) and non-Euclidean diffusion equations. I will show that drawing on methods from the domain of differential geometry, it is possible to provide a principled view on such GNN architectural choices as positional encoding and graph rewiring as well as explain and remedy the phenomena of oversquashing and bottlenecks.