Federated split GANs for collaborative training with heterogeneous devices

Liang, Yilei, Kortoçi, Pranvera, Zhou, Pengyuan, Lee, Lik-Hang, Mehrabidavoodabadi, Abbas, Hui, Pan, Tarkoma, Sasu and Crowcroft, Jon (2022) Federated split GANs for collaborative training with heterogeneous devices. Software Impacts, 14. p. 100436. ISSN 2665-9638

1-s2.0-S2665963822001208-main.pdf - Published Version
Available under License Creative Commons Attribution 4.0.

Download (329kB) | Preview
Official URL: https://doi.org/10.1016/j.simpa.2022.100436


Applications based on machine learning (ML) are greatly facilitated by mobile devices and their enormous volume and variety of data. To better safeguard the privacy of user data, traditional ML techniques have transitioned toward new paradigms like federated learning (FL) and split learning (SL). However, existing frameworks have overlooked device heterogeneity, greatly hindering their applicability in practice. In order to address such limitations, we developed a framework based on both FL and SL to share the training load of the discriminative part of a GAN to different client devices. We make our framework available as open-source software1.

Item Type: Article
Uncontrolled Keywords: Federated learning, Split learning, GAN, Hardware heterogeneous, Privacy preservation
Subjects: G600 Software Engineering
Department: Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User: Elena Carlaw
Date Deposited: 20 Dec 2022 15:03
Last Modified: 20 Dec 2022 15:15
URI: https://nrl.northumbria.ac.uk/id/eprint/50966

Actions (login required)

View Item View Item


Downloads per month over past year

View more statistics