Privacy-Preserving Federated Primal-Dual Learning for Non-Convex and Non-Smooth Problems With Model Sparsification

Yiwei Li, Chien Wei Huang, Shuai Wang, Chong Yung Chi, Tony Q.S. Quek

研究成果: Article同行評審


Federated learning (FL) has been recognized as a rapidly growing research area, where the model is trained over massively distributed clients under the orchestration of a parameter server (PS) without sharing clients’ data. This paper delves into a class of federated problems characterized by non-convex and non-smooth loss functions, that are prevalent in FL applications but challenging to handle due to their intricate non-convexity and non-smoothness nature and the conflicting requirements on communication efficiency and privacy protection. In this paper, we propose a novel federated primal-dual algorithm with bidirectional model sparsification tailored for non-convex and non-smooth FL problems, and differential privacy is applied for privacy guarantee. Its unique insightful properties and some privacy and convergence analyses are also presented as the FL algorithm design guidelines. Extensive experiments on real-world data are conducted to demonstrate the effectiveness of the proposed algorithm and much superior performance than some state-of-the-art FL algorithms, together with the validation of all the analytical results and properties.

頁(從 - 到)1
期刊IEEE Internet of Things Journal
出版狀態Accepted/In press - 2024

All Science Journal Classification (ASJC) codes

  • 訊號處理
  • 資訊系統
  • 硬體和架構
  • 電腦科學應用
  • 電腦網路與通信


深入研究「Privacy-Preserving Federated Primal-Dual Learning for Non-Convex and Non-Smooth Problems With Model Sparsification」主題。共同形成了獨特的指紋。