Are Targeted Messages More Effective?

arXiv:2403.06817v1 Announce Type: cross
Abstract: Graph neural networks (GNN) are deep learning architectures for graphs. Essentially, a GNN is a distributed message passing algorithm, which is controlled by parameters learned from data. It operates on the vertices of a graph: in each iteration, vertices receive a message on each incoming edge, aggregate these messages, and then update their state based on their current state and the aggregated messages. The expressivity of GNNs can be characterised in terms of certain fragments …

abstract algorithm architectures arxiv cs.ai cs.lg cs.lo data deep learning distributed edge gnn graph graph neural networks graphs iteration messages networks neural networks parameters type