IJIS_FinalSubmission.pdf (1.45 MB)
On the game-theoretic analysis of distributed generative adversarial networks
journal contribution
posted on 2021-11-16, 10:16 authored by Zhongguo Li, Zhen Dong, Wen-Hua ChenWen-Hua Chen, Zhengtao DingIn this paper, a distributed method is proposed for training multiple generative adversarial networks (GANs) with private data sets via a game-theoretic approach. To facilitate the requirement of privacy protection, distributed training algorithms offer a promising solution to learn global models without sample exchanges. Existing studies have mainly concentrated on training neural networks using pure cooperation strategies, which are not suitable for GANs. This paper develops a new framework for distributed GANs, where two groups of discriminators and generators are involved in a zero-sum game. Under connected graphs, such a framework is reformulated as a constrained minmax optimisation problem. Then, a fully distributed training algorithm is proposed without exchanging any private data samples. The convergence of the proposed algorithm is established via advanced consensus and optimisation techniques. Simulation studies are presented to validate the effectiveness of the proposed framework and algorithm.
History
School
- Aeronautical, Automotive, Chemical and Materials Engineering
Department
- Aeronautical and Automotive Engineering
Published in
International Journal of Intelligent SystemsVolume
37Issue
1Pages
516-534Publisher
WileyVersion
- AM (Accepted Manuscript)
Rights holder
© Wiley Periodicals LLCPublisher statement
This is the peer reviewed version of the following article: LI, Z. ... et al, 2022. On the game-theoretic analysis of distributed generative adversarial networks. International Journal of Intelligent Systems, 37 (1), pp.516-534, which has been published in final form at https://doi.org/10.1002/int.22637. This article may be used for non-commercial purposes in accordance with Wiley Terms and Conditions for Use of Self-Archived Versions. This article may not be enhanced, enriched or otherwise transformed into a derivative work, without express permission from Wiley or by statutory rights under applicable legislation. Copyright notices must not be removed, obscured or modified. The article must be linked to Wiley’s version of record on Wiley Online Library and any embedding, framing or otherwise making available the article or pages thereof by third parties from platforms, services and websites other than Wiley Online Library must be prohibited.Acceptance date
2021-08-11Publication date
2021-09-03Copyright date
2021ISSN
0884-8173eISSN
1098-111XPublisher version
Language
- en