mlsanityData to 14 Oct 2026

Space-Time Graph Neural Networks with Stochastic Graph Perturbations

arXiv 2210.16270 ↗First posted 28 Oct 2022cs.LG eess.SPcited by 5

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 19 of its 25 references that are in the map. First posted on arXiv 28 Oct 2022.

Builds on

19 of 25 references.

References · 19

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2019Simplifying Graph Convolutional Networkscited by 1,477
  3. 2019Stability Properties of Graph Neural Networkscited by 127
  4. 2020Graphon Neural Networks and the Transferability of Graph Neural Networkscited by 118
  5. 2019Transferability of Spectral Graph Convolutional Neural Networkscited by 92
  6. 2019Stability and Generalization of Graph Convolutional Neural Networkscited by 81
  7. 2020Convergence and Stability of Graph Convolutional Networks on Large Random Graphscited by 76
  8. 2019Learning Decentralized Controllers for Robot Swarms with Graph Neural Networkscited by 62
  9. 2021Transferability of Graph Neural Networks: an Extended Graphon Approachcited by 53
  10. 2020Message-Aware Graph Attention Networks for Large-Scale Multi-Robot Path Planningcited by 43
  11. 2021Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Studycited by 36
  12. 2022Multi-Robot Collaborative Perception with Graph Neural Networkscited by 35
7 more
  1. 2020Distributed Scheduling using Graph Neural Networkscited by 27
  2. 2020On the Stability of Graph Convolutional Neural Networks under Edge Rewiringcited by 25
  3. 2021Stability of Graph Convolutional Neural Networks to Stochastic Perturbationscited by 18
  4. 2020Graph Neural Network for Large-Scale Network Localizationcited by 11
  5. 2021Space-Time Graph Neural Networkscited by 10
  6. 2021On the Stability of Low Pass Graph Filter With a Large Number of Edge Rewirescited by 5
  7. 2021Optimal Solving of Constrained Path-Planning Problems with Graph Convolutional Networks and Optimized Tree Searchcited by 3

Built on by

Cited by year

Citing papers per year: 2023: 4; 2024: 0; 2025: 1.

5 papers.

  1. 2023Robust Stochastically-Descending Unrolled Networkscited by 9
  2. 2023Stochastic Unrolled Federated Learningcited by 6
  3. 2023Learning Decentralized Flocking Controllers with Spatio-Temporal Graph Neural Networkcited by 2
  4. 2023Learning Graph ARMA Processes from Time-Vertex Spectracited by 1
  5. 2025Unrolled Graph Neural Networks for Constrained Optimizationcited by 1