no code implementations • 25 Mar 2024 • Jiaojiao Zhang, Linglingzhi Zhu, Mikael Johansson
We propose a novel differentially private algorithm for online federated learning that employs temporally correlated noise to improve the utility while ensuring the privacy of the continuously released models.
no code implementations • 4 Sep 2023 • Jiaojiao Zhang, Jiang Hu, Mikael Johansson
We propose a novel algorithm for solving the composite Federated Learning (FL) problem.
no code implementations • 2 Aug 2023 • Jiaojiao Zhang, Dominik Fay, Mikael Johansson
This paper proposes a locally differentially private federated learning algorithm for strongly convex but possibly nonsmooth problems that protects the gradients of each worker against an honest but curious server.
no code implementations • 27 Feb 2023 • Xiangtao Wang, Ruizhi Wang, Biao Tian, Jiaojiao Zhang, Shuo Zhang, Junyang Chen, Thomas Lukasiewicz, Zhenghua Xu
We leverage the masked patches selection strategy to choose masked patches with lesions to obtain more lesion representation information, and the adaptive masking strategy is utilized to help learn more mutual information and improve performance further.
no code implementations • 21 Oct 2020 • Hao Zheng, Jidun Wu, Qilu Cao, Jiaojiao Zhang, Xiaojiang Huang
Compared with the dual-frequency (DF) CCPs, it is found that with the increase of IF power, the HF power can control the electron density more independently with less influence on the electron temperature.
Plasma Physics