# Graph Attention Inference of Network Topology in Multi-Agent Systems

arXiv: https://arxiv.org/abs/2408.15449 · HTML: https://mlsanity.com/paper/2408.15449/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 26 references that are in the map.
- First posted on arXiv 27 Aug 2024.

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Graph Signal Processing: Overview, Challenges and Applications](https://mlsanity.com/paper/1712.00468/) (2017)
- [Connecting the Dots: Identifying Network Structure via Graph Signal Processing](https://mlsanity.com/paper/1810.13066/) (2018)
- [Network Inference from Consensus Dynamics with Unknown Parameters](https://mlsanity.com/paper/1908.01393/) (2019)
- [Reward-Sharing Relational Networks in Multi-Agent Reinforcement Learning as a Framework for Emergent Behavior](https://mlsanity.com/paper/2207.05886/) (2022)
- [Networks in Cognitive Science](https://mlsanity.com/paper/1304.6736/) (2013)
- [Impact of Relational Networks in Multi-Agent Learning: A Value-Based Factorization View](https://mlsanity.com/paper/2310.12912/) (2023)
- [Energy-Guided Data Sampling for Traffic Prediction with Mini Training Datasets](https://mlsanity.com/paper/2403.18710/) (2024)
- [Learning to Identify Graphs from Node Trajectories in Multi-Robot Networks](https://mlsanity.com/paper/2307.04374/) (2023)

## Abstract (arXiv)

Accurately identifying the underlying graph structures of multi-agent systems remains a difficult challenge. Our work introduces a novel machine learning-based solution that leverages the attention mechanism to predict future states of multi-agent systems by learning node representations. The graph structure is then inferred from the strength of the attention values. This approach is applied to both linear consensus dynamics and the non-linear dynamics of Kuramoto oscillators, resulting in implicit learning of the graph by learning good agent representations. Our results demonstrate that the presented data-driven graph attention machine learning model can identify the network topology in multi-agent systems, even when the underlying dynamic model is not known, as evidenced by the F1 scores achieved in the link prediction.