Contextualized Messages Boost Graph Representations

arXiv:2403.12529v1 Announce Type: new
Abstract: Graph neural networks (GNNs) have gained significant interest in recent years due to their ability to handle arbitrarily structured data represented as graphs. GNNs generally follow the message-passing scheme to locally update node feature representations. A graph readout function is then employed to create a representation for the entire graph. Several studies proposed different GNNs by modifying the aggregation and combination strategies of the message-passing framework, often inspired by heuristics. Nevertheless, several studies have begun …

abstract arxiv boost cs.lg data feature function gnns graph graph neural networks graphs messages networks neural networks node representation structured data type update