arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.15449cs.MAcs.LG
收藏

多智能体系统中网络拓扑的图注意力推断

Graph Attention Inference of Network Topology in Multi-Agent Systems

University of Massachusetts Lowell(马萨诸塞大学洛厄尔分校)

Akshay Kolli, Reza Azadeh, Kshitj Jerath

AI总结:

针对多智能体系统底层图结构难以识别的问题,提出利用注意力机制学习节点表示并依据注意力强度推断网络拓扑的数据驱动模型,在未知动力学下仍取得良好链路预测 F1 分数。

摘要:

准确识别多智能体系统的底层图结构仍是一项困难挑战。我们的工作提出了一种新颖的基于机器学习的解决方案,该方案利用注意力机制,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。该方法被应用于线性一致性动力学和 Kuramoto 振子的非线性动力学,通过学习良好的智能体表示实现了对图的隐式学习。我们的结果表明,所提出的数据驱动图注意力机器学习模型能够识别多智能体系统中的网络拓扑,即使在底层动态模型未知时也是如此,链路预测中取得的 F1 分数证明了这一点。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑