Enhancing Convergence in Federated Learning: A Contribution-Aware Asynchronous Approach

no code implementations • 16 Feb 2024 • Changxin Xu, Yuxin Qiao, Zhanxin Zhou, Fanghao Ni, Jize Xiong

However, most of these methods simply aggregate all of the received updates without considering their relative contributions, which can slow down convergence.

Federated Learning