no code implementations • 23 May 2023 • Yi-Rui Yang, Chang-Wei Shi, Wu-Jun Li
However, for existing BRDL methods, large batch sizes will lead to a drop on model accuracy, even if there is no Byzantine attack.
no code implementations • 9 Mar 2023 • Yi-Rui Yang, Kun Wang, Wu-Jun Li
Based on ConSpar, we further propose a novel FL framework called FedREP, which is Byzantine-robust, communication-efficient and privacy-preserving.
no code implementations • 2 Mar 2020 • Yi-Rui Yang, Wu-Jun Li
In this paper, we propose a novel method, called buffered asynchronous stochastic gradient descent (BASGD), for ABL.