Expander Graph Propagation

by   Andreea Deac, et al.

Deploying graph neural networks (GNNs) on whole-graph classification or regression tasks is known to be challenging: it often requires computing node features that are mindful of both local interactions in their neighbourhood and the global context of the graph structure. GNN architectures that navigate this space need to avoid pathological behaviours, such as bottlenecks and oversquashing, while ideally having linear time and space complexity requirements. In this work, we propose an elegant approach based on propagating information over expander graphs. We provide an efficient method for constructing expander graphs of a given size, and use this insight to propose the EGP model. We show that EGP is able to address all of the above concerns, while requiring minimal effort to set up, and provide evidence of its empirical utility on relevant datasets and baselines in the Open Graph Benchmark. Importantly, using expander graphs as a template for message passing necessarily gives rise to negative curvature. While this appears to be counterintuitive in light of recent related work on oversquashing, we theoretically demonstrate that negatively curved edges are likely to be required to obtain scalable message passing without bottlenecks. To the best of our knowledge, this is a previously unstudied result in the context of graph representation learning, and we believe our analysis paves the way to a novel class of scalable methods to counter oversquashing in GNNs.


page 1

page 2

page 3

page 4


Make Heterophily Graphs Better Fit GNN: A Graph Rewiring Approach

Graph Neural Networks (GNNs) are popular machine learning methods for mo...

FoSR: First-order spectral rewiring for addressing oversquashing in GNNs

Graph neural networks (GNNs) are able to leverage the structure of graph...

Understanding over-squashing and bottlenecks on graphs via curvature

Most graph neural networks (GNNs) use the message passing paradigm, in w...

My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Control

Multitask Reinforcement Learning is a promising way to obtain models wit...

Characterizing Graph Datasets for Node Classification: Beyond Homophily-Heterophily Dichotomy

Homophily is a graph property describing the tendency of edges to connec...

Understanding Oversquashing in GNNs through the Lens of Effective Resistance

Message passing graph neural networks are popular learning architectures...

Oversquashing in GNNs through the lens of information contraction and graph expansion

The quality of signal propagation in message-passing graph neural networ...

Please sign up or login with your details

Forgot password? Click here to reset