FlGan: GAN-Based Unbiased Federated Learning Under Non-IID Settings
Zhuoran Ma, Yang Liu, Yinbin Miao, Guowen Xu, Ximeng Liu, Jianfeng Ma, Robert H. Deng
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 <small>FlGan</small> , to mitigate local biases using synthesized samples generated by GAN while preserving user-level privacy in the FL setting. Specifically, <small>FlGan</small> 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, <small>FlGan</small> then exploits Fully Homomorphic Encryption (FHE) to design the privacy-preserving GAN augmentation method for the unbiased FL. Extensive experiments show that <small>FlGan</small> achieves unbiased FL with <inline-formula><tex-math notation="LaTeX">$10\%-60\%$</tex-math></inline-formula> 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 <small>FlGan</small> .