Communication-Efficient Personalized Federated Learning via Layer-Wise Multi-Threshold Random Sketching
This work proposes a communication-efficient PFL framework via layer-wise multi-threshold random sketching that supports bidirectional communication using compact low-bit sketches and improves the communication-accuracy tradeoff compared with existing one-bit compression approaches.
Xu Zhang, Xing-Yu Hou, Jia-Cheng Cheng et al.
· 0 citations