🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

#GNNs are related to PDEs governing information diffusion on graphs. In a new paper with @b_p_chamberlain James Rowbottom Maria Gorinova Stefan Webb Emanuele Rossi we study a new class of Neural Graph Diffusion PDEs Blog post: bit.ly/3gUOEL8 Paper: arxiv.org/abs/2106.10934

1/4 Hope to see friends new & old tomorrow 4:30pm GMT / 8:30am PT poster session 6 #NeurIPS2021 James Rowbottom Francesco Di Giovanni and I will occupy the prime virtual real estate known as Spot E3 with BLEND neurips.cc/virtual/2021/p…

I am happy to share a recent work on energy functionals giving rise to GNN equations via gradient flows 🧵 arxiv.org/abs/2206.10991 This is joint work with James Rowbottom*, @b_p_chamberlain, T. Markovich, and Michael Bronstein

Looking forward to giving an invited (and in-person!) talk in Jure Leskovec's group tomorrow Stanford University. I'll talk about our latest take on physics-inspired learning on graphs using non-linear oscillators. arxiv: arxiv.org/abs/2202.02296 code: github.com/tk-rusch/Graph… w/ Michael Bronstein

Equivariant Mesh Attention Networks Sourya Basu, Jose Gallego-Posada, Francesco Viganò, James Rowbottom, Taco Cohen openreview.net/forum?id=3IqqJ…

Here is last week's video of Francesco Di Giovanni, James Rowbottom and @b_p_chamberlain presenting their paper "Graph Neural Networks as Gradient Flows"! youtu.be/sgTTtmwOMgE

This is a super accessible explanation* of our gradient flow work and it's based on a recent arXiv version contanining new theoretical results and experiments *Beware, great meme ahead

@thomaskipf and Max Welling strike back! in a new blog post w/ Francesco Di Giovanni James Rowbottom et al we show that GCN-type models can be derived as gradient flows of Dirichlet-type energy and provably avoid low-frequency dominated dynamics bit.ly/3TdhTLg