no code implementations • 15 Mar 2023 • Tao Liu, Zhi Wang, Hui He, Liangliang Lin, Wei Shi, Ran An, Chenhao Li
Experiments show that under different Non-IID experiment settings, our method can reduce the upload communication cost to about 2. 9% to 18. 9% of the conventional federated learning algorithm when the sparse rate is 0. 01.