Generalization of Graph Neural Networks through the Lens of Homomorphism

arXiv:2403.06079v1 Announce Type: new
Abstract: Despite the celebrated popularity of Graph Neural Networks (GNNs) across numerous applications, the ability of GNNs to generalize remains less explored. In this work, we propose to study the generalization of GNNs through a novel perspective - analyzing the entropy of graph homomorphism. By linking graph homomorphism with information-theoretic measures, we derive generalization bounds for both graph and node classifications. These bounds are capable of capturing subtleties inherent in various graph structures, including but not …

abstract applications arxiv cs.lg entropy gnns graph graph neural networks networks neural networks novel perspective study through type work