Space-Time Graph Neural Networks with Stochastic Graph Perturbations
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.
Cite
@article{arxiv.2210.16270,
title = {Space-Time Graph Neural Networks with Stochastic Graph Perturbations},
author = {Samar Hadou and Charilaos Kanatsoulis and Alejandro Ribeiro},
journal= {arXiv preprint arXiv:2210.16270},
year = {2022}
}