Statistical Guarantees for Link Prediction using Graph Neural Networks

Understand

This paper derives statistical guarantees for the performance of Graph Neural Networks (GNNs) in link prediction tasks on graphs generated by a graphon.

• We propose a linear GNN architecture (LG-GNN) that produces consistent estimators for the underlying edge probabilities.
• We establish a bound on the mean squared error and give guarantees on the ability of LG-GNN to detect high-probability edges.
• Our guarantees hold for both sparse and dense graphs.