Space-Time Graph Neural Networks with Stochastic Graph Perturbations

Samar Hadou; Charilaos I. Kanatsoulis; Alejandro Ribeiro

ICASSP 2023accepted0 citations

Space-Time Graph Neural Networks with Stochastic Graph Perturbations

Samar Hadou, Charilaos I. Kanatsoulis, Alejandro Ribeiro

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.

BibTeX

@inproceedings{icassp2023_spacetimegraphne,
  title = {Space-Time Graph Neural Networks with Stochastic Graph Perturbations},
  author = {Samar Hadou and Charilaos I. Kanatsoulis and Alejandro Ribeiro},
  booktitle = {ICASSP 2023},
  year = {2023}
}