Stability of Graph Convolutional Neural Networks to Stochastic Perturbations

Abstract

Graph convolutional neural networks (GCNNs) are nonlinear processing tools to learn representations from network data. A key property of GCNNs is their stability to graph perturbations. Current analysis considers deterministic perturbations but fails to provide relevant insights when topological changes are random. This paper investigates the stability of GCNNs to stochastic graph perturbations induced by link losses. In particular, it proves the expected output difference between the GCNN over random perturbed graphs and the GCNN over the nominal graph is upper bounded by a factor that is linear in the link loss probability. We perform the stability analysis in the graph spectral domain such that the result holds uniformly for any graph. This result also shows the role of the nonlinearity and the architecture width and depth, and allows identifying handle to improve the GCNN robustness. Numerical simulations on source localization and robot swarm control corroborate our theoretical findings.

References in corpus (10)

• Discrete Signal Processing on Graphs
• Adversarial Attacks on Neural Networks for Graph Data
• Optimal Wireless Resource Allocation with Random Edge Graph Neural Networks
• Convolutional Neural Network Architectures for Signals Supported on Graphs
• Sensor Networks with Random Links: Topology Design for Distributed Consensus
• Stability Properties of Graph Neural Networks
• Advances in Distributed Graph Filtering
• Filtering Random Graph Processes Over Random Time-Varying Graphs
• Diffusion Scattering Transforms on Graphs
• Graph and graphon neural network stability