Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

How Universal Polynomial Bases Enhance Spectral Graph Neural Networks: Heterophily, Over-smoothing, and Over-squashing

About

Spectral Graph Neural Networks (GNNs), alternatively known as graph filters, have gained increasing prevalence for heterophily graphs. Optimal graph filters rely on Laplacian eigendecomposition for Fourier transform. In an attempt to avert prohibitive computations, numerous polynomial filters have been proposed. However, polynomials in the majority of these filters are predefined and remain fixed across different graphs, failing to accommodate the varying degrees of heterophily. Addressing this gap, we demystify the intrinsic correlation between the spectral property of desired polynomial bases and the heterophily degrees via thorough theoretical analyses. Subsequently, we develop a novel adaptive heterophily basis wherein the basis vectors mutually form angles reflecting the heterophily degree of the graph. We integrate this heterophily basis with the homophily basis to construct a universal polynomial basis UniBasis, which devises a polynomial filter based graph neural network - UniFilter. It optimizes the convolution and propagation in GNN, thus effectively limiting over-smoothing and alleviating over-squashing. Our extensive experiments, conducted on a diverse range of real-world and synthetic datasets with varying degrees of heterophily, support the superiority of UniFilter. These results not only demonstrate the universality of UniBasis but also highlight its proficiency in graph explanation.

Keke Huang, Yu Guang Wang, Ming Li, and Pietro Li\`o• 2024

Related benchmarks

TaskDatasetResultRank
Node ClassificationCiteseer
Accuracy77.8
1037
Node ClassificationChameleon
Accuracy41.2
867
Node ClassificationSquirrel
Accuracy33.1
786
Node ClassificationRoman-Empire
Accuracy74.5
327
Node Classificationamazon-ratings
Accuracy42.43
309
Node ClassificationPhysics
Accuracy93.1
205
Node ClassificationMinesweeper
Accuracy86.8
113
Node Classificationquestions
Accuracy96.2
64
Node ClassificationCS
Accuracy92.8
61
Showing 9 of 9 rows

Other info

Follow for update