​​'Graph Neural Networks through the lens of algebraic topology, differential geometry, and PDEs'

A recent talk by Prof. Michael Bronstein (University of Oxford, Twitter), delivered in-person at the Computer Laboratory, University of Cambridge.

The talk is centred around the idea that graphs can be viewed as a discretisation of an underlying continuous manifold. This physics-inspired approach opens up a new trove of tools from the fields of differential geometry, algebraic topology, and differential equations so far largely unexplored in graph ML.

Recording: https://www.cl.cam.ac.uk/seminars/wednesday/video/20220309-1500-t170978.html
Associated Blogpost: https://towardsdatascience.com/graph-neural-networks-beyond-weisfeiler-lehman-and-vanilla-message-passing-bc8605fa59a