Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
EFFGAN: Ensembles of fine-tuned federated GANs
RISE Research Institutes of Sweden, Digital Systems, Data Science.
RISE Research Institutes of Sweden, Digital Systems, Data Science.ORCID iD: 0000-0001-7856-113X
RISE Research Institutes of Sweden, Digital Systems, Data Science.ORCID iD: 0000-0002-9567-2218
2022 (English)Conference paper, Published paper (Refereed)
Abstract [en]

Decentralized machine learning tackles the problemof learning useful models when data is distributed amongseveral clients. The most prevalent decentralized setting todayis federated learning (FL), where a central server orchestratesthe learning among clients. In this work, we contribute to therelatively understudied sub-field of generative modelling in theFL framework.We study the task of how to train generative adversarial net-works (GANs) when training data is heterogeneously distributed(non-iid) over clients and cannot be shared. Our objective isto train a generator that is able to sample from the collectivedata distribution centrally, while the client data never leaves theclients and user privacy is respected. We show using standardbenchmark image datasets that existing approaches fail in thissetting, experiencing so-called client drift when the local numberof epochs becomes to large and local parameters drift too faraway in parameter space. To tackle this challenge, we proposea novel approach namedEFFGAN: Ensembles of fine-tunedfederated GANs. Being an ensemble of local expert generators, EFFGAN is able to learn the data distribution over all clientsand mitigate client drift. It is able to train with a large numberof local epochs, making it more communication efficient thanprevious works

Place, publisher, year, edition, pages
2022.
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:ri:diva-62532DOI: 10.48550/arXiv.2206.11682OAI: oai:DiVA.org:ri-62532DiVA, id: diva2:1726787
Conference
2022 IEEE International Conference on Big Data, 2022 IEEE International Conference on Big Data
Available from: 2023-01-13 Created: 2023-01-13 Last updated: 2024-05-21Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textFull ttext

Authority records

Zec, Edvin ListoMogren, Olof

Search in DiVA

By author/editor
Zec, Edvin ListoMogren, Olof
By organisation
Data Science
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 287 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf