mlsanityData to 7 Oct 2026

Graph Neural Networks Gone Hogwild

arXiv 2407.00494 ↗First posted 29 Jun 2024cs.LG cs.DCcited by 2

Not on the map. Why?

Abstract (arXiv)

Graph neural networks (GNNs) appear to be powerful tools to learn state representations for agents in distributed, decentralized multi-agent systems, but generate catastrophically incorrect predictions when nodes update asynchronously during inference. This failure under asynchrony effectively excludes these architectures from many potential applications where synchrony is difficult or impossible to enforce, e.g., robotic swarms or sensor networks. In this work we identify "implicitly-defined" GNNs as a class of architectures which is provably robust to asynchronous "hogwild" inference, adapting convergence guarantees from work in asynchronous and distributed optimization. We then propose a novel implicitly-defined GNN architecture, which we call an 'energy GNN'. We show that this architecture outperforms other GNNs from this class on a variety of synthetic tasks inspired by multi-agent systems.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 27 of its 55 references that are in the map. First posted on arXiv 29 Jun 2024.

Builds on

27 of 55 references.

References · 27

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2018How Powerful are Graph Neural Networks?cited by 4,355
  5. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  6. 2016Input Convex Neural Networkscited by 407
  7. 2022Long Range Graph Benchmarkcited by 258
  8. 2018Learning Attentional Communication for Multi-Agent Cooperationcited by 170
  9. 2018Graph Convolutional Reinforcement Learningcited by 148
  10. 2021Interpreting and Unifying Graph Neural Networks with An Optimization Frameworkcited by 131
  11. 2020A Unified View on Graph Neural Networks as Graph Signal Denoisingcited by 110
  12. 2020Implicit Graph Neural Networkscited by 98
15 more
  1. 2019Graph Neural Networks for Decentralized Multi-Robot Path Planningcited by 84
  2. 2021DistGNN: Scalable Distributed Training for Large-Scale Graph Neural Networkscited by 59
  3. 2021Dorylus: Affordable, Scalable, and Accurate GNN Training with Distributed CPU Servers and Serverless Threadscited by 51
  4. 2022PipeGCN: Efficient Full-Graph Training of Graph Convolutional Networks with Pipelined Feature Communicationcited by 45
  5. 2021Learning Graph Cellular Automatacited by 33
  6. 2022EIGNN: Efficient Infinite-Depth Graph Neural Networkscited by 32
  7. 2022Parallel and Distributed Graph Neural Networks: An In-Depth Concurrency Analysiscited by 29
  8. 2019Graph Policy Gradients for Large Scale Robot Controlcited by 27
  9. 2021Graph Neural Networks for Decentralized Multi-Robot Submodular Action Selectioncited by 13
  10. 2021Coverage Control in Multi-Robot Systems via Graph Neural Networkscited by 13
  11. 2023Asynchronous Algorithmic Alignment with Cocyclescited by 13
  12. 2019Deep Reinforcement Learning-Based Channel Allocation for Wireless LANs with Graph Convolutional Networkscited by 12
  13. 2020Synthesizing Decentralized Controllers with Graph Neural Networks and Imitation Learningcited by 12
  14. 2021Implicit vs Unfolded Graph Neural Networkscited by 12
  15. 2021A Framework for Real-World Multi-Robot Systems Running Decentralized GNN-Based Policiescited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systemscited by 1
  2. 2026RAMP: Recognition parametrisation by Amortised Message Passingcited by 0