To promote better performance-bandwidth trade-off for multi-agent perception, weproposeanovel distilledcollaborationgraph (DiscoGraph)tomodeltrainable, pose-aware, and adaptive collaboration among agents. Our key novelties lie in twoaspects.

Hence, a "fair" reward allocation scheme is desirable to give all parties enough incentives to join the collaboration.

UCB, wherein agents cooperatively minimize the group regret under the coordination of a central server.

Federated learning (FL), through its privacy-preserving collaborative learning approach, has significantly empowered decentralized devices.

However, due to the heterogeneity between the clients' data distributions, the model obtained through the use of FL algorithms may perform poorly on some client's data.