VC dimension of Graph Neural Networks with Pfaffian activation functions

arXiv:2401.12362v2 Announce Type: replace-cross
Abstract: Graph Neural Networks (GNNs) have emerged in recent years as a powerful tool to learn tasks across a wide range of graph domains in a data-driven fashion; based on a message passing mechanism, GNNs have gained increasing popularity due to their intuitive formulation, closely linked with the Weisfeiler-Lehman (WL) test for graph isomorphism, to which they have proven equivalent. From a theoretical point of view, GNNs have been shown to be universal approximators, and their …

abstract arxiv cs.lg data data-driven domains fashion functions gnns graph graph neural networks learn networks neural networks stat.ml tasks tool type