Statistical Guarantees for Link Prediction using Graph Neural Networks
Machine Learning
2024-02-08 v2 Social and Information Networks
Statistics Theory
Machine Learning
Statistics Theory
Abstract
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. Finally, we demonstrate some of the shortcomings of the classical GCN architecture, as well as verify our results on real and synthetic datasets.
Cite
@article{arxiv.2402.02692,
title = {Statistical Guarantees for Link Prediction using Graph Neural Networks},
author = {Alan Chung and Amin Saberi and Morgane Austern},
journal= {arXiv preprint arXiv:2402.02692},
year = {2024}
}