Open access
Aug 2026
FedDecouple: Mitigating Noise Accumulation in Differentially Private Federated Learning via Phase Decoupling
FedDecouple is proposed, a phase-decoupled differentially private federated learning framework that is analytically suited for resource-constrained mobile devices and significantly outperforming client-side noised DP-SGD on MNIST and CIFAR-10.
Teng-Hang Ge, Xiaochao Wei
· Mathematics · 0 citations