An Effective Universal Polynomial Basis for Spectral Graph Neural Networks

arXiv:2311.18177v2 Announce Type: replace
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 …

abstract arxiv cs.lg cs.si eess.sp filters fourier gnns graph graph neural networks graphs networks neural networks polynomial type universal