HFL-GAN: scalable hierarchical federated learning GAN for high quantity heterogeneous clients

Petch, Lewis; Moustafa, Ahmed; Ma, Xinhui; Yasser, Mohammad

Abstract

This paper introduces a novel approach for training generative adversarial networks using federated machine learning. Generative adversarial networks have gained plenty of attention in the research community especially with their abilities to produce high quality synthetic data for a variety of use-cases. Yet, when combined with federated learning, those models suffer from degradation in both training time and quality of results. To address this challenge, this paper introduces a novel approach that uses hierarchical learning techniques to enable the efficient training of federated GAN models. The proposed approach introduces an innovative mechanism that dynamically clusters participant clients to edge servers as well as a novel multi-generator GAN architecture that utilizes non-identical model aggregation stages. The proposed approach has been evaluated on a number of benchmark datasets to measure its performance on higher numbers of participating clients. The results show that HFL-GAN outperforms other comparative state-of-the-art approaches in the training of GAN models in complex non-IID federated learning settings.

Citation

Petch, L., Moustafa, A., Ma, X., & Yasser, M. (2025). HFL-GAN: scalable hierarchical federated learning GAN for high quantity heterogeneous clients. Applied Intelligence, 55(2), Article 170. https://doi.org/10.1007/s10489-024-05924-x

• Journal Article Type: Article
• Acceptance Date: Oct 19, 2024
• Online Publication Date: Dec 16, 2024
• Publication Date: Jan 1, 2025
• Deposit Date: Dec 16, 2024
• Publicly Available Date: Dec 17, 2024
• Journal: Applied Intelligence
• Print ISSN: 0924-669X
• Publisher: Springer (part of Springer Nature)
• Peer Reviewed: Peer Reviewed
• Volume: 55
• Issue: 2
• Article Number: 170
• DOI: https://doi.org/10.1007/s10489-024-05924-x
• Keywords: Federated learning; Generative adversarial network; Non-IID; Hierarchical learning
• Public URL: https://hull-repository.worktribe.com/output/4963799
• Publisher URL: https://link.springer.com/article/10.1007/s10489-024-05924-x?utm_source=rct_congratemailt&utm_medium=email&utm_campaign=oa_20241216&utm_content=10.1007/s10489-024-05924-x