New post @TDataScience about physics-inspired "continuous" graph ML models
🧵
bit.ly/3pxxx7q 1/ The message-passing paradigm has been the "battle horse" of deep learning on graphs for several years, making graph neural networks a big success in a wide range of applications, from particle physics to protein design.

New blog post coauthored with @cottascience @ffabffrasca @HaggaiMaron @chrsmrrs Lingxiao Zhao on a new class of "Subgraph GNN" architectures that are more expressive than WL test

michael-bronstein.medium.com/using-subgraph… Several recent works (some of which we review in the post) leverage the idea of removing nodes/edges from the graph in order to resolve some of the ambiguities leading to the failure of the WL test

Over-squashing is a common plight of GNNs occurring when message passing fails to propagate information efficiently on the graph. In a new post, we discuss how this phenomenon can be understood and remedied through the concept of Ricci curvature

michael-bronstein.medium.com/over-squashing… Collaboration between @TwitterEng #Cortex and @UniofOxford Jake Topping Francesco Di Giovanni @b_p_chamberlain Xiaowen Dong

Details in the paper: arxiv.org/pdf/2111.14522…

Some personal news: I will be joining @CompSciOxford @UniofOxford as @DeepMind chair in #AI and Fellow at @ExeterCollegeOx I owe this honour to the amazing students and collaborators with whom I have had the privilege to work during my career

https://twitter.com/CompSciOxford/status/1465282742007078912

I would like to thank the HoD Leslie Goldberg and former HoD @wooldridgemike for their support and patience that allowed this appointment to happen

After a hiatus, a new series of blogs posts. Do differential geometry and algebraic topology sound too exotic for ML? In recent works, we show that tools from these fields bring a new perspective on graph neural networks

First post in the series:

towardsdatascience.com/graph-neural-n… Based on recent works with @CristianBodnar @ffabffrasca @kneppkatt @wangyg85 @pl219_Cambridge @guidomontufar @b_p_chamberlain @migorinova @stefan_webb @emaros96 @aittalam James Rowbottom, Jake Topping, Xiaowen Dong, Francesco Di Giovanni

The recording of my #inaugural talk at @imperialcollege is now available online



This geometric view on deep learning is the convergence of many old and recent research threads and joint work with @joanbruna @PetarV_93 and @TacoCohen Joan's 2014 paper on spectral #graphneuralnetworks was my inspiration to get into this field and write our paper with him, @ylecun @trekkinglemon and Arthur Szlam that popularized the term #geometricdeeplearning

In summer 2020, I started writing a blog on #GraphML in @TDataScience

towardsdatascience.com/graph-deep-lea…

It was a new and rewarding experience, from which I learned a lot. I was surprised that such a technical topic would attract >200K views and >6K claps in less than half a year. I am grateful to all the readers and colleagues whom I used as "guinea pigs" to proof-read my posts especially @frederickmonti @emaros96 @b_p_chamberlain @ffabffrasca @gbouritsas @__lucab @fhuszar and to @kmborgwardt @thomaskipf @guennemann whose comments helped improve them