# Graph Neural Networks for Decentralized Controllers

arXiv: https://arxiv.org/abs/2003.10280 · HTML: https://mlsanity.com/paper/2003.10280/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Mar 2020.

## Built on by (most cited first, 14 of 14)

- [Transferability Properties of Graph Neural Networks](https://mlsanity.com/paper/2112.04629/) (2021)
- [Graph Neural Networks in IoT: A Survey](https://mlsanity.com/paper/2203.15935/) (2022)
- [Decentralized Inference with Graph Neural Networks in Wireless Communication Systems](https://mlsanity.com/paper/2104.09027/) (2021)
- [Predicting Basin Stability of Power Grids using Graph Neural Networks](https://mlsanity.com/paper/2108.08230/) (2021)
- [Robust Graph Neural Networks via Probabilistic Lipschitz Constraints](https://mlsanity.com/paper/2112.07575/) (2021)
- [Communication Topology Co-Design in Graph Recurrent Neural Network Based Distributed Control](https://mlsanity.com/paper/2104.13868/) (2021)
- [Privacy-Preserving Decentralized Inference with Graph Neural Networks in Wireless Networks](https://mlsanity.com/paper/2208.06963/) (2022)
- [Toward Dynamic Stability Assessment of Power Grid Topologies using Graph Neural Networks](https://mlsanity.com/paper/2206.06369/) (2022)
- [Optimal Solving of Constrained Path-Planning Problems with Graph Convolutional Networks and Optimized Tree Search](https://mlsanity.com/paper/2108.01036/) (2021)
- [Towards dynamic stability analysis of sustainable power grids using graph neural networks](https://mlsanity.com/paper/2212.11130/) (2022)
- [Decentralized Statistical Inference with Unrolled Graph Neural Networks](https://mlsanity.com/paper/2104.01555/) (2021)
- [Solving Disjunctive Temporal Networks with Uncertainty under Restricted Time-Based Controllability using Tree Search and Graph Neural Networks](https://mlsanity.com/paper/2203.15030/) (2022)
- [Transferability of Convolutional Neural Networks in Stationary Learning Tasks](https://mlsanity.com/paper/2307.11588/) (2023)
- [A Gated Graph Neural Network Approach to Fast-Convergent Dynamic Average Estimation](https://mlsanity.com/paper/2606.20955/) (2026)

## Abstract (arXiv)

Dynamical systems comprised of autonomous agents arise in many relevant problems such as multi-agent robotics, smart grids, or smart cities. Controlling these systems is of paramount importance to guarantee a successful deployment. Optimal centralized controllers are readily available but face limitations in terms of scalability and practical implementation. Optimal decentralized controllers, on the other hand, are difficult to find. In this paper, we propose a framework using graph neural networks (GNNs) to learn decentralized controllers from data. While GNNs are naturally distributed architectures, making them perfectly suited for the task, we adapt them to handle delayed communications as well. Furthermore, they are equivariant and stable, leading to good scalability and transferability properties. The problem of flocking is explored to illustrate the potential of GNNs in learning decentralized controllers.