MULTI-FLGANs: Multi Distributed Adversarial Networks for Non-IID distributed datasets

Bachelor thesis (2022)

Authors

A. Amalan Electrical Engineering, Mathematics and Computer Science

Contributors

K. Liang Cyber Security - EEMCS (mentor)
R. Wang Cyber Security - EEMCS (mentor)
Julián Urbano (graduation committee member)
Faculty
Electrical Engineering, Mathematics and Computer Science, Electrical Engineering, Mathematics and Computer Science
Copyright: © 2022 Akash Amalan
More Info
expand_more

Published Date

22-06-2022

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Electrical Engineering, Mathematics and Computer Science

Abstract

Federated learning is an emerging concept in the domain of distributed machine learning. This concept has enabled GANs to benefit from the rich distributed training data while preserving privacy However,in a non-iid setting, current federated GAN architectures are unstable, struggling to learn the distinct features and vulnerable to mode collapse. In this paper, we propose a novel architecture MULTIFLGAN to solve the problem of low-quality images, mode collapse and instability for non-iid datasets. Our results show that MULTI-FLGAN is four times as stable and performant (i.e. high inception score) on average over 20 clients compared to baseline FLGAN.