Logo image
Privacy-Preserving Federated Primal-Dual Learning for Nonconvex and Nonsmooth Problems With Model Sparsification
Journal article

Privacy-Preserving Federated Primal-Dual Learning for Nonconvex and Nonsmooth Problems With Model Sparsification

Yiwei Li, Chien-Wei Huang, Shuai Wang, Chong-Yung Chi and Tony Q. S. Quek
IEEE internet of things journal, Vol.11(15), pp.25853-25866
01/08/2024

Abstract

Computer Science Computer Science, Information Systems Engineering Engineering, Electrical & Electronic Science & Technology Technology Telecommunications
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 article delves into a class of federated problems characterized by nonconvex and nonsmooth (NCNS) loss functions, that are prevalent in FL applications but challenging to handle due to their intricate nonconvexity and nonsmoothness nature and the conflicting requirements on communication efficiency and privacy protection. In this article, we propose a novel federated primal-dual algorithm with bidirectional model sparsification tailored for NCNS 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.

Metrics

1 Record Views

Details

Logo image