English

Training Federated GANs with Theoretical Guarantees: A Universal Aggregation Approach

Machine Learning 2021-02-10 v1 Artificial Intelligence

Abstract

Recently, Generative Adversarial Networks (GANs) have demonstrated their potential in federated learning, i.e., learning a centralized model from data privately hosted by multiple sites. A federatedGAN jointly trains a centralized generator and multiple private discriminators hosted at different sites. A major theoretical challenge for the federated GAN is the heterogeneity of the local data distributions. Traditional approaches cannot guarantee to learn the target distribution, which isa mixture of the highly different local distributions. This paper tackles this theoretical challenge, and for the first time, provides a provably correct framework for federated GAN. We propose a new approach called Universal Aggregation, which simulates a centralized discriminator via carefully aggregating the mixture of all private discriminators. We prove that a generator trained with this simulated centralized discriminator can learn the desired target distribution. Through synthetic and real datasets, we show that our method can learn the mixture of largely different distributions where existing federated GAN methods fail.

Keywords

Cite

@article{arxiv.2102.04655,
  title  = {Training Federated GANs with Theoretical Guarantees: A Universal Aggregation Approach},
  author = {Yikai Zhang and Hui Qu and Qi Chang and Huidong Liu and Dimitris Metaxas and Chao Chen},
  journal= {arXiv preprint arXiv:2102.04655},
  year   = {2021}
}
R2 v1 2026-06-23T22:58:10.941Z