Optimizing Polynomial Graph Filters: A Novel Adaptive Krylov Subspace Approach

arXiv:2403.07954v1 Announce Type: new
Abstract: Graph Neural Networks (GNNs), known as spectral graph filters, find a wide range of applications in web networks. To bypass eigendecomposition, polynomial graph filters are proposed to approximate graph filters by leveraging various polynomial bases for filter training. However, no existing studies have explored the diverse polynomial graph filters from a unified perspective for optimization.
In this paper, we first unify polynomial graph filters, as well as the optimal filters of identical degrees into the …

abstract applications arxiv cs.lg eess.sp filter filters gnns graph graph neural networks however networks neural networks novel polynomial studies training type web