Jake Topping

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

@krasul @Francesco_dgv @b_p_chamberlain @epomqo @mmbronstein Not that I know of, a happy coincidence!🙂

@jctopping @Francesco_dgv @b_p_chamberlain @epomqo @mmbronstein Awesome work! BTW are you related to Peter Topping? Would be a funny coincidence!

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_dgv @b_p_chamberlain @epomqo @mmbronstein (arxiv.org/abs/2111.14522)

This Tuesday in LoGaG @Francesco_dgv @jctopping 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

Great article from @PetarV_93 and @mmbronstein on another exciting year of Geometric ML to come, and excited to see our recent work on curvature rewiring and bottlenecks with @Francesco_dgv @b_p_chamberlain @epomqo and @mmbronstein featured. Bring on 2022!

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…

@idarbwire #O3Y9 #rainbow

@idarbwire #O3Y9 #bomb