AI RESEARCH
Different Statistical Perspectives for Understanding Generalisation in Graph Neural Networks
arXiv CS.LG
•
ArXi:2605.25452v1 Announce Type: cross Graph Neural Networks (GNN) are currently the most popular approach for learning and prediction on graph-structured data and are deployed in various fields, from social network analysis to drug discovery. However, there is limited mathematical understanding of the performance of GNNs. We discuss the various perspectives used to study statistical generalisation in GNNs. We identify three broad frameworks.