CKGConv: General Graph Convolution with Continuous Kernels

arXiv:2404.13604v1 Announce Type: new
Abstract: The existing definitions of graph convolution, either from spatial or spectral perspectives, are inflexible and not unified. Defining a general convolution operator in the graph domain is challenging due to the lack of canonical coordinates, the presence of irregular structures, and the properties of graph symmetries. In this work, we propose a novel graph convolution framework by parameterizing the kernels as continuous functions of pseudo-coordinates derived via graph positional encoding. We name this Continuous Kernel …

abstract arxiv canonical continuous convolution cs.ai cs.lg definitions domain general graph perspectives spatial the graph type