Convergence and Stability of Graph Convolutional Networks on Large Random Graphs - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year :

Convergence and Stability of Graph Convolutional Networks on Large Random Graphs

Abstract

We study properties of Graph Convolutional Networks (GCNs) by analyzing their behavior on standard models of random graphs, where nodes are represented by random latent variables and edges are drawn according to a similarity kernel. This allows us to overcome the difficulties of dealing with discrete notions such as isomorphisms on very large graphs, by considering instead more natural geometric aspects. We first study the convergence of GCNs to their continuous counterpart as the number of nodes grows. Our results are fully non-asymptotic and are valid for relatively sparse graphs with an average degree that grows logarithmically with the number of nodes. We then analyze the stability of GCNs to small deformations of the random graph model. In contrast to previous studies of stability in discrete settings, our continuous setup allows us to provide more intuitive deformation-based metrics for understanding stability, which have proven useful for explaining the success of convolutional representations on Euclidean domains.

Dates and versions

hal-02976711 , version 1 (23-10-2020)

Identifiers

Cite

Nicolas Keriven, Alberto Bietti, Samuel Vaiter. Convergence and Stability of Graph Convolutional Networks on Large Random Graphs. NeurIPS 2020 - 34th Conference on Neural Information Processing Systems, Dec 2020, Vancouver (virtual), Canada. ⟨hal-02976711⟩
3788 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More