×
Jun 8, 2022 · In this paper, we propose Dap-FL, a deep deterministic policy gradient (DDPG)-assisted adaptive FL system, in which local learning rates and local training ...
In this article, we propose Dap-FL, a deep deterministic policy gradient (DDPG)-assisted adaptive FL system, in which local learning rates and local training ...
Dap-FL: Federated Learning flourishes by adaptive tuning and secure aggregation. Implemented based on Tensorflow. The copyright of the code in this project ...
Specifically, it improves accuracy by 0.4% and requires 1.1× fewer rounds against the best-performing baseline, FEDDYN. In [250] , DAP-FL, the authors use ...
May 8, 2023 · In addition, the privacy of clients is preserved by a pro- posed secure aggregation procedure, where local contributions are doubly masked based ...
People also ask
Dap-FL: Federated Learning Flourishes by Adaptive Tuning and Secure Aggregation. IEEE Trans. Parallel Distributed Syst. 34(6): 1923-1941 (2023). [c5]. view.
In this paper, we propose Dap-FL, a deep deterministic policy gradient (DDPG)-assisted adaptive FL system, in which local learning rates and local training ...
A recipe for auto-tuning communication-efficient secure aggregation is developed, based on specific properties of random rotation and secure aggregation ...
Jul 17, 2024 · Dap-fl: Federated learning flourishes by adaptive tuning and secure aggregation. IEEE Transactions on Parallel and Distributed Systems, 2023 ...
... Training Tasks on GPU With Fine-Grained Kernel Fusion pp. 1968-1981. Dap-FL: Federated Learning Flourishes by Adaptive Tuning and Secure Aggregation pp. 1923 ...