Communication-Efficient Learning of Deep Networks from Decentralized Data, H. Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Agüera y Arcas, 2017Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS), Vol. 54 (PMLR) - 这篇基础论文介绍了联邦平均(FedAvg)算法,它是许多后续联邦学习算法的基准,其局限性正是 FedProx 旨在解决的问题。