Graphon Cross-Validation: Assessing Models on Network Data

ICLR 2026 Conference Submission15109 Authors

Keywords: Graphon, Link prediction, Cross-Validation, Graph imputa- tion, Selection consistency

Abstract:

Graphon models have emerged as powerful tools for modeling complex network structures by capturing connection probabilities among nodes. A key challenge in their application lies in accurately characterizing the graphon function, particularly with respect to parameters that govern its smoothness, which significantly impact the estimation accuracy. In this article, we propose a novel graphon cross-validation method for selecting tuning parameters and estimation approaches.
Our method is both theoretically sound and computationally efficient.
We show that our proposed cross-validation score is asymptotically parallel to the estimation error. Through extensive simulations and real-world applications, we demonstrate that our method consistently delivers superior computational efficiency and accuracy.

Primary Area: learning on graphs and other geometries & topologies

Submission Number: 15109