Tackling Graph Oversquashing by Global and Local Non-Dissipativity

arXiv:2405.01009v1 Announce Type: new
Abstract: A common problem in Message-Passing Neural Networks is oversquashing -- the limited ability to facilitate effective information flow between distant nodes. Oversquashing is attributed to the exponential decay in information transmission as node distances increase. This paper introduces a novel perspective to address oversquashing, leveraging properties of global and local non-dissipativity, that enable the maintenance of a constant information flow rate. Namely, we present SWAN, a uniquely parameterized model GNN with antisymmetry both in space …

abstract arxiv cs.lg flow global graph information networks neural networks node nodes novel paper perspective type