# Graph Neural Networks Gone Hogwild

arXiv: https://arxiv.org/abs/2407.00494 · HTML: https://mlsanity.com/paper/2407.00494/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 55 references that are in the map.
- First posted on arXiv 29 Jun 2024.

## Builds on (most cited first, 27 of 27)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Input Convex Neural Networks](https://mlsanity.com/paper/1609.07152/) (2016)
- [Long Range Graph Benchmark](https://mlsanity.com/paper/2206.08164/) (2022)
- [Learning Attentional Communication for Multi-Agent Cooperation](https://mlsanity.com/paper/1805.07733/) (2018)
- [Graph Convolutional Reinforcement Learning](https://mlsanity.com/paper/1810.09202/) (2018)
- [Interpreting and Unifying Graph Neural Networks with An Optimization Framework](https://mlsanity.com/paper/2101.11859/) (2021)
- [A Unified View on Graph Neural Networks as Graph Signal Denoising](https://mlsanity.com/paper/2010.01777/) (2020)
- [Implicit Graph Neural Networks](https://mlsanity.com/paper/2009.06211/) (2020)
- [Graph Neural Networks for Decentralized Multi-Robot Path Planning](https://mlsanity.com/paper/1912.06095/) (2019)
- [DistGNN: Scalable Distributed Training for Large-Scale Graph Neural Networks](https://mlsanity.com/paper/2104.06700/) (2021)
- [Dorylus: Affordable, Scalable, and Accurate GNN Training with Distributed CPU Servers and Serverless Threads](https://mlsanity.com/paper/2105.11118/) (2021)
- [PipeGCN: Efficient Full-Graph Training of Graph Convolutional Networks with Pipelined Feature Communication](https://mlsanity.com/paper/2203.10428/) (2022)
- [Learning Graph Cellular Automata](https://mlsanity.com/paper/2110.14237/) (2021)
- [EIGNN: Efficient Infinite-Depth Graph Neural Networks](https://mlsanity.com/paper/2202.10720/) (2022)
- [Parallel and Distributed Graph Neural Networks: An In-Depth Concurrency Analysis](https://mlsanity.com/paper/2205.09702/) (2022)
- [Graph Policy Gradients for Large Scale Robot Control](https://mlsanity.com/paper/1907.03822/) (2019)
- [Graph Neural Networks for Decentralized Multi-Robot Submodular Action Selection](https://mlsanity.com/paper/2105.08601/) (2021)
- [Coverage Control in Multi-Robot Systems via Graph Neural Networks](https://mlsanity.com/paper/2109.15278/) (2021)
- [Implicit vs Unfolded Graph Neural Networks](https://mlsanity.com/paper/2111.06592/) (2021)
- [Asynchronous Algorithmic Alignment with Cocycles](https://mlsanity.com/paper/2306.15632/) (2023)
- [Deep Reinforcement Learning-Based Channel Allocation for Wireless LANs with Graph Convolutional Networks](https://mlsanity.com/paper/1905.07144/) (2019)
- [Synthesizing Decentralized Controllers with Graph Neural Networks and Imitation Learning](https://mlsanity.com/paper/2012.14906/) (2020)
- [A Framework for Real-World Multi-Robot Systems Running Decentralized GNN-Based Policies](https://mlsanity.com/paper/2111.01777/) (2021)

## Built on by (most cited first, 2 of 2)

- [When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems](https://mlsanity.com/paper/2607.06807/) (2026)
- [RAMP: Recognition parametrisation by Amortised Message Passing](https://mlsanity.com/paper/2607.18883/) (2026)

## 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.