Part of Advances in Neural Information Processing Systems 35 (NeurIPS 2022) Main Conference Track
Yangze Zhou, Gitta Kutyniok, Bruno Ribeiro
This work provides the first theoretical study on the ability of graph Message Passing Neural Networks (gMPNNs) ---such as Graph Neural Networks (GNNs)--- to perform inductive out-of-distribution (OOD) link prediction tasks, where deployment (test) graph sizes are larger than training graphs. We first prove non-asymptotic bounds showing that link predictors based on permutation-equivariant (structural) node embeddings obtained by gMPNNs can converge to a random guess as test graphs get larger. We then propose a theoretically-sound gMPNN that outputs structural pairwise (2-node) embeddings and prove non-asymptotic bounds showing that, as test graphs grow, these embeddings converge to embeddings of a continuous function that retains its ability to predict links OOD. Empirical results on random graphs show agreement with our theoretical results.