Publication Type
Journal Article
Version
acceptedVersion
Publication Date
4-2024
Abstract
Federated Learning (FL) suffers from low convergence and significant accuracy loss due to local biases caused by non-Independent and Identically Distributed (non-IID) data. To enhance the non-IID FL performance, a straightforward idea is to leverage the Generative Adversarial Network (GAN) to mitigate local biases using synthesized samples. Unfortunately, existing GAN-based solutions have inherent limitations, which do not support non-IID data and even compromise user privacy. To tackle the above issues, we propose a GAN-based unbiased FL scheme, called FlGan, to mitigate local biases using synthesized samples generated by GAN while preserving user-level privacy in the FL setting. Specifically, FlGan first presents a federated GAN algorithm using the divide-and-conquer strategy that eliminates the problem of model collapse in non-IID settings. To guarantee user-level privacy, FlGan then exploits Fully Homomorphic Encryption (FHE) to design the privacy-preserving GAN augmentation method for the unbiased FL. Extensive experiments show that FlGan achieves unbiased FL with 10%−60%10%−60% accuracy improvement compared with two state-of-the-art FL baselines (i.e., FedAvg and FedSGD) trained under different non-IID settings. The FHE-based privacy guarantees only cost about 0.53% of the total overhead in FlGan.
Keywords
Federated learning, fully homomorphic encryption, GAN, non-IID, user-level privacy
Discipline
Databases and Information Systems | Information Security
Research Areas
Information Systems and Management
Publication
IEEE Transactions on Knowledge and Data Engineering
Volume
36
Issue
4
First Page
1566
Last Page
1581
ISSN
1041-4347
Identifier
10.1109/TKDE.2023.3309858
Publisher
Institute of Electrical and Electronics Engineers
Citation
MA, Zhuoran; LIU, Yang; MIAO, Yinbin; XU, Guowen; LIU, Ximeng; MA, Jianfeng; and DENG, Robert H..
FlGan: GAN-based unbiased federated learning under non-IID settings. (2024). IEEE Transactions on Knowledge and Data Engineering. 36, (4), 1566-1581.
Available at: https://ink.library.smu.edu.sg/sis_research/8743
Copyright Owner and License
Authors
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1109/TKDE.2023.3309858