FlGan: GAN-based unbiased federated learning under non-IID settings

• Main Authors: MA, Zhuoran, LIU, Yang, MIAO, Yinbin, XU, Guowen, LIU, Ximeng, MA, Jianfeng, DENG, Robert H.
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Federated learning; fully homomorphic encryption; GAN; non-IID; user-level privacy; Databases and Information Systems; Information Security
• Online Access: https://ink.library.smu.edu.sg/sis_research/8743; https://ink.library.smu.edu.sg/context/sis_research/article/9746/viewcontent/FlGan_av.pdf
• Institution: Singapore Management University

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.