Space-Time Graph Neural Networks with Stochastic Graph Perturbations

TL;DR

This paper demonstrates that space-time graph neural networks are stable under stochastic graph perturbations, enabling better transfer learning and generalized architectures for time-varying data, validated through control system experiments.

Contribution

It proves the stability of ST-GNNs to stochastic perturbations and introduces generalized architectures for joint processing of dynamic graphs and signals.

Findings

ST-GNNs are stable under stochastic graph perturbations.

The proposed architectures improve transfer learning on dynamic graphs.

Experimental validation on control systems confirms theoretical insights.

Abstract

Space-time graph neural networks (ST-GNNs) are recently developed architectures that learn efficient graph representations of time-varying data. ST-GNNs are particularly useful in multi-agent systems, due to their stability properties and their ability to respect communication delays between the agents. In this paper we revisit the stability properties of ST-GNNs and prove that they are stable to stochastic graph perturbations. Our analysis suggests that ST-GNNs are suitable for transfer learning on time-varying graphs and enables the design of generalized convolutional architectures that jointly process time-varying graphs and time-varying signals. Numerical experiments on decentralized control systems validate our theoretical results and showcase the benefits of traditional and generalized ST-GNN architectures.