activity
20212024
most citedUnderstanding over-squashing and bottlenecks on graphs via curvature

34 citations · 85 across the 8 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2024★ 1 cited

Metric Flow Matching for Smooth Interpolations on the Data Manifold

Kacper Kapuśniak, Peter Potaptchik, Teodora Reu +5

Matching objectives underpin the success of modern generative models and rely on constructing conditional paths that transform a source distribution into a target distribution. Des…

cs.LG2024★ 2 cited

A General Graph Spectral Wavelet Convolution via Chebyshev Order Decomposition

Nian Liu, Xiaoxin He, Thomas Laurent +3

Spectral graph convolution, an important tool of data filtering on graphs, relies on two essential decisions: selecting spectral bases for signal transformation and parameterizing…

cs.LG2024★ 1 cited

Understanding Virtual Nodes: Oversquashing and Node Heterogeneity

Joshua Southern, Francesco Di Giovanni, Michael Bronstein +1

While message passing neural networks (MPNNs) have convincing success in a range of applications, they exhibit limitations such as the oversquashing problem and their inability to…

cs.LG2023

Locality-Aware Graph-Rewiring in GNNs

Federico Barbero, Ameya Velingker, Amin Saberi +2

Graph Neural Networks (GNNs) are popular models for machine learning on graphs that typically follow the message-passing paradigm, whereby the feature of a node is updated recursiv…

cs.LG2023★ 4 cited

DRew: Dynamically Rewired Message Passing with Delay

Benjamin Gutteridge, Xiaowen Dong, Michael Bronstein +1

Message passing neural networks (MPNNs) have been shown to suffer from the phenomenon of over-squashing that causes poor performance for tasks relying on long-range interactions. T…

cs.LG2023★ 31 cited

On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and Topology

Francesco Di Giovanni, Lorenzo Giusti, Federico Barbero +3

Message Passing Neural Networks (MPNNs) are instances of Graph Neural Networks that leverage the graph to send messages over the edges. This inductive bias leads to a phenomenon kn…