An Effective Universal Polynomial Basis for Spectral Graph Neural Networks

TL;DR

This paper introduces UniBasis, a universal polynomial basis for spectral GNNs that adapts to graph heterophily levels, improving filter approximation without costly eigendecomposition.

Contribution

The paper develops an adaptive heterophily basis integrated with a homophily basis to form a universal polynomial basis for spectral GNNs, enhancing flexibility across diverse graphs.

Findings

UniFilter outperforms existing polynomial filters on various datasets.

The universal basis effectively captures heterophily variations.

Experimental results demonstrate improved accuracy and generality.

Abstract

Spectral Graph Neural Networks (GNNs), also referred to 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 the prohibitive computations, numerous polynomial filters by leveraging distinct polynomials have been proposed to approximate the desired graph filters. However, polynomials in the majority of polynomial filters are predefined and remain fixed across all graphs, failing to accommodate the diverse heterophily degrees across different graphs. To tackle this issue, we first investigate the correlation between polynomial bases of desired graph filters and the degrees of graph heterophily via a thorough theoretical analysis. Afterward, we develop an adaptive heterophily basis by incorporating graph heterophily degrees. Subsequently, we integrate this heterophily basis with the homophily basis, creating a universal polynomial basis UniBasis. In consequence, we devise a general polynomial filter UniFilter. Comprehensive experiments on both real-world and synthetic datasets with varying heterophily degrees significantly support the superiority of UniFilter, demonstrating the effectiveness and generality of UniBasis, as well as its promising capability as a new method for graph analysis.