GraphComm: Efficient Graph Convolutional Communication for Multi-Agent Cooperation

Artificial intelligence empowered smart things (e.g., robots, autonomous vehicles, and unmanned aerial vehicles) have been transforming the world. The “brains” of smart things can be abstracted as the agents or cybertwins residing on end devices and edge servers. The next generation communication networks (i.e., 6G) will become the nervous system for these agents and natively support multi-agent cooperation. By sharing local observations and intentions via communication channels, the agents could better understand the environments and make right decisions. Due to the limited channel bandwidth, the communication is considered as a bottleneck of multi-agent cooperation. In this paper, we propose a graph convolutional communication method (GraphComm) for multi-agent cooperation to relive the bottleneck. Specifically, a variational information bottleneck is used to encode the observations and intentions compactly. Furthermore, a graph information bottleneck with attention-based neighbor sampling mechanism is utilized to improve the effectiveness and robustness of the multi-round communication process. The experimental results show that GraphComm can improve the effectiveness, robustness and efficiency of communication in multi-agent cooperative tasks as compared with baseline methods.