Graph Attention Inference of Network Topology in Multi-Agent Systems
This addresses the challenge of network topology inference for researchers in multi-agent systems, but it is incremental as it builds on existing attention-based methods.
The paper tackles the problem of identifying underlying graph structures in multi-agent systems by introducing a machine learning model that uses attention mechanisms to predict future states and infer topology from attention values, achieving results demonstrated by F1 scores in link prediction.
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.