Space-Time Graph Neural Networks with Stochastic Graph Perturbations
This work addresses stability issues for ST-GNNs in multi-agent systems, offering incremental improvements for applications like decentralized control.
The paper tackled the stability of space-time graph neural networks (ST-GNNs) under stochastic graph perturbations, proving their robustness and enabling transfer learning on time-varying graphs, with numerical experiments validating these results in decentralized control systems.
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.