Federated split GANs for collaborative training with heterogeneous devices

Yilei Liang, Pranvera Kortoçi*, Pengyuan Zhou, Lik Hang Lee, Abbas Mehrabidavoodabadi, Pan Hui, Sasu Tarkoma, Jon Crowcroft

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

2 Downloads (Pure)

Abstract

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.

Original languageEnglish
Article number100436
Number of pages3
JournalSoftware Impacts
Volume14
Early online date29 Oct 2022
DOIs
Publication statusPublished - 4 Nov 2022

Fingerprint

Dive into the research topics of 'Federated split GANs for collaborative training with heterogeneous devices'. Together they form a unique fingerprint.

Cite this