PFL-GAN: When Client Heterogeneity Meets Generative Models in Personalized Federated Learning

TL;DR

PFL-GAN introduces a novel personalized federated learning approach using GANs that accounts for client heterogeneity by learning client similarities and employing weighted data aggregation, improving model personalization.

Contribution

It proposes a new GAN sharing and aggregation strategy for personalized federated learning that effectively handles client heterogeneity.

Findings

Demonstrates the effectiveness of PFL-GAN on multiple datasets.

Shows improved personalization over traditional global GAN models.

Validates the approach through rigorous experiments.

Abstract

Recent advances of generative learning models are accompanied by the growing interest in federated learning (FL) based on generative adversarial network (GAN) models. In the context of FL, GAN can capture the underlying client data structure, and regenerate samples resembling the original data distribution without compromising the private raw data. Although most existing GAN-based FL works focus on training a global model, Personalized FL (PFL) sometimes can be more effective in view of client data heterogeneity in terms of distinct data sample distributions, feature spaces, and labels. To cope with client heterogeneity in GAN-based FL, we propose a novel GAN sharing and aggregation strategy for PFL. The proposed PFL-GAN addresses the client heterogeneity in different scenarios. More specially, we first learn the similarity among clients and then develop an weighted collaborative data aggregation. The empirical results through the rigorous experimentation on several well-known datasets demonstrate the effectiveness of PFL-GAN.