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…

Great article from Petar Veličković and Michael Bronstein on another exciting year of Geometric ML to come, and excited to see our recent work on curvature rewiring and bottlenecks with Francesco Di Giovanni @b_p_chamberlain xiaowen dong and Michael Bronstein featured. Bring on 2022!

Thrilled that our paper "Understanding over-squashing and bottlenecks on graphs via curvature" has been accepted for an oral presentation at #ICLR2022! Big thank you to the team Francesco Di Giovanni @b_p_chamberlain xiaowen dong Michael Bronstein (arxiv.org/abs/2111.14522)

This Tuesday in LoGaG Francesco Di Giovanni Jake Topping and @b_p_chamberlain present their "Understanding over-squashing and bottlenecks on graphs via curvature" arxiv.org/abs/2111.14522 - an absolute super-star paper from #iclr2022!🚀 Join the meeting here: hannes-stark.com/logag-reading-… 1/2

An in-depth and very well-explained walkthrough of our recent paper (that we're presenting at ICLR tomorrow and Wednesday!) - thank you Aleksa!