Graph Attention Inference of Network Topology in Multi-Agent Systems
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
MUST: Multi-Scale Structural-Temporal Link Prediction Model for UAV Ad Hoc Networks
Graph Attention for Heterogeneous Graphs with Positional Encoding
LASE: Learned Adjacency Spectral Embeddings
Utilizing Graph Neural Networks for Effective Link Prediction in Microservice Architectures
Perturbation Ontology based Graph Attention Networks
HGATE: Heterogeneous Graph Attention Auto-Encoders
토론
이 논문과 연결된 포럼 글이 아직 없습니다.