Understanding over-squashing and bottlenecks on graphs via curvature · HackerPapers discussions

Understanding over-squashing and bottlenecks on graphs via curvature — mentioned by stefanpie

Tue, 19 Sep 2023 16:33:24 GMT

I've work with GNNs. I have not explicitly looked into this, but in general, the dynamics of GNNs are really interesting and there are many different lenses in which one can study the behavior of GNNs and find interesting takeaways. - Explicit Message Passing: https://arxiv.org/abs/2202.11097 - Algorithmic Reasoning: https://arxiv.org/abs/2203.15544 - Diffusion: https://proceedings.mlr.press/v139/chamberlain21a.html - Spectral: https://arxiv.org/abs/2010.02863 - Sparsity: https://arxiv.org/abs/2211.15335 - Training Tricks: https://arxiv.org/abs/2108.10521 - Interaction Networks / Physical…

Paper and discussion history. A mention is not an endorsement.

Understanding over-squashing and bottlenecks on graphs via curvature — mentioned by ajb117

Tue, 19 Sep 2023 16:33:10 GMT

Besides the the title being a bit exaggerated, it's been long-acknowledged in the GNN community that graph rewiring often helps learning; see [1, 2] for example. Also, at first skim, I'm surprised there's no discussion on oversmoothing/oversquashing in this paper. It seems like what they're calling "overfitting" on the graph structure could be interpreted as the GNN's node representations saturating/starving because of poor graph topology. [1] - https://arxiv.org/abs/2111.14522 [2] - https://arxiv.org/abs/2210.02997

Paper and discussion history. A mention is not an endorsement.