Homophily modulates double descent generalization in graph convolution networks.

ABSTRACT: Graph neural networks (GNNs) excel in modeling relational data such as biological, social, and transportation networks, but the underpinnings of their success are not well understood. Traditional complexity measures from statistical learning theory fail to account for observed phenomena like the double descent or the impact of relational semantics on generalization error. Motivated by experimental observations of "transductive" double descent in key networks and datasets, we use analytical tools from statistical physics and random matrix theory to precisely characterize generalization in simple graph convolution networks on the contextual stochastic block model. Our results illuminate the nuances of learning on homophilic versus heterophilic data and predict double descent whose existence

SUBMITTER: Shi C 

PROVIDER: S-EPMC10895367 | biostudies-literature | 2024 Feb

REPOSITORIES: biostudies-literature