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.

翻译：准确识别多智能体系统的底层图结构仍然是一个具有挑战性的难题。本研究提出了一种基于机器学习的新方法，该方法利用注意力机制通过学习节点表示来预测多智能体系统的未来状态。随后根据注意力值的强度推断图结构。该方法在线性一致性动力学和Kuramoto振荡器的非线性动力学中均得到应用，通过学习优质的智能体表示实现了对图的隐式学习。实验结果表明，所提出的数据驱动图注意力机器学习模型能够有效识别多智能体系统的网络拓扑结构，即使在底层动力学模型未知的情况下也能实现，这在链路预测任务中取得的F1分数得到了验证。