no code implementations • 18 Mar 2024 • Ziru Niu, Hai Dong, A. K. Qin
This approach ensures that a portion of the local model remains personalized, thereby enhancing the model's robustness against biased parameters from other clients.
1 code implementation • 15 Oct 2023 • Ziru Niu, Hai Dong, A. Kai Qin, Tao Gu
Under the orchestration of a server, edge devices (also called clients in FL) collaboratively train a global deep-learning model without sharing any local data.