Spectral GNN via Two-dimensional (2-D) Graph Convolution

arXiv:2404.04559v1 Announce Type: new
Abstract: Spectral Graph Neural Networks (GNNs) have achieved tremendous success in graph learning. As an essential part of spectral GNNs, spectral graph convolution extracts crucial frequency information in graph data, leading to superior performance of spectral GNNs in downstream tasks. However, in this paper, we show that existing spectral GNNs remain critical drawbacks in performing the spectral graph convolution. Specifically, considering the spectral graph convolution as a construction operation towards target output, we prove that existing …

abstract arxiv convolution cs.lg cs.na data eess.sp gnn gnns graph graph data graph learning graph neural networks however information math.na networks neural networks paper part performance show success tasks type via