Locality-Aware Graph-Rewiring in GNNs

arXiv:2310.01668v2 Announce Type: replace
Abstract: Graph Neural Networks (GNNs) are popular models for machine learning on graphs that typically follow the message-passing paradigm, whereby the feature of a node is updated recursively upon aggregating information over its neighbors. While exchanging messages over the input graph endows GNNs with a strong inductive bias, it can also make GNNs susceptible to over-squashing, thereby preventing them from capturing long-range interactions in the given graph. To rectify this issue, graph rewiring techniques have been …

abstract arxiv bias cs.lg feature gnns graph graph neural networks graphs inductive information machine machine learning messages neighbors networks neural networks node paradigm popular type while