Multi-Agent Path Finding (MAPF) is a representative multi-agent coordination problem, where multiple agents are required to navigate to their respective goals without collisions. Solving MAPF optimally is known to be NP-hard, leading to the adoption of learning-based approaches to alleviate the online computational burden. Prevailing approaches, such as Graph Neural Networks (GNNs), are typically constrained to pairwise message passing between agents. However, this limitation leads to suboptimal behaviours and critical issues, such as attention dilution, particularly in dense environments where group (i.e. beyond just two agents) coordination is most critical. Despite the importance of such higher-order interactions, existing approaches have not been able to fully explore them. To address this representational bottleneck, we introduce HMAGAT (Hypergraph Multi-Agent Attention Network), a novel architecture that leverages attentional mechanisms over directed hypergraphs to explicitly capture group dynamics. Empirically, HMAGAT establishes a new state-of-the-art among learning-based MAPF solvers: e.g., despite having just 1M parameters and being trained on 100$\times$ less data, it outperforms the current SoTA 85M parameter model. Through detailed analysis of HMAGAT's attention values, we demonstrate how hypergraph representations mitigate the attention dilution inherent in GNNs and capture complex interactions where pairwise methods fail. Our results illustrate that appropriate inductive biases are often more critical than the training data size or sheer parameter count for multi-agent problems.
Learning from Heterogeneity: A Dynamic Learning Framework for Hypergraphs
School of Computer Science and Technology, Tongji University(同济大学计算机科学与技术学院);Ant Group(蚂蚁集团);School of Computer Science and Artificial Intelligence, Wuhan University of Technology(武汉理工大学计算机科学与人工智能学院);School of Computer Science, Fudan University(复旦大学计算机学院);School of Science, Computing and Engineering Technologies, Swinburne University of Technology(斯威本科技大学科学、计算与工程技术学院)
Stability and Generalization of Hypergraph Collaborative Networks
Institute of Data Science, The University of Hong Kong(香港大学数据科学学院);College of Information Science and Technology, Jinan University(暨南大学信息科学技术学院);The University of Hong Kong(香港大学)
Context-Aware Hypergraph Construction for Robust Spectral Clustering
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);The University of Adelaide(阿德莱德大学);State University of New York, Binghamton(纽约州立大学宾汉姆顿分校)
Hyper-STTN: Hypergraph Augmented Spatial-Temporal Transformer Network for Trajectory Prediction
School of Applied and Creative Computing, Purdue University(普渡大学应用与创意计算学院);Department of Computer Science and Department of Intelligent Systems Engineering, Indiana University Bloomington(印第安纳大学布卢明顿分校计算机科学系和智能系统工程系);Department of Applied Artificial Intelligence, Sungkyunkwan University(成均馆大学应用人工智能系)
A Framework for Directed Acyclic Hypergraph Learning
Institute for Financial Services Analytics, University of Delaware(特拉华大学金融服务分析研究所);Department of Electrical and Computer Engineering, University of Delaware(特拉华大学电气与计算机工程系);Department of Applied Economics and Statistics, University of Delaware(特拉华大学应用经济学与统计学系);Department of Electrical and Computer Engineering, University of Kentucky(肯塔基大学电气与计算机工程系)