Lying Graph Convolution: Learning to Lie for Node Classification Tasks

arXiv:2405.01247v1 Announce Type: new
Abstract: In the context of machine learning for graphs, many researchers have empirically observed that Deep Graph Networks (DGNs) perform favourably on node classification tasks when the graph structure is homophilic (\ie adjacent nodes are similar). In this paper, we introduce Lying-GCN, a new DGN inspired by opinion dynamics that can adaptively work in both the heterophilic and the homophilic setting. At each layer, each agent (node) shares its own opinions (node embeddings) with its neighbours. …

abstract arxiv classification context convolution cs.lg cs.si graph graphs machine machine learning networks node nodes paper researchers tasks the graph type