2 papers
cs.LG2022
Contrastive Identity-Aware Learning for Multi-Agent Value Decomposition
Shunyu Liu, Yihe Zhou, Jie Song +5
Value Decomposition (VD) aims to deduce the contributions of agents for decentralized policies in the presence of only global rewards, and has recently emerged as a powerful credit…
cs.LG2022
HIRE: Distilling High-order Relational Knowledge From Heterogeneous Graph Neural Networks
Jing Liu, Tongya Zheng, Qinfen Hao
Researchers have recently proposed plenty of heterogeneous graph neural networks (HGNNs) due to the ubiquity of heterogeneous graphs in both academic and industrial areas. Instead…