Umeå universitets logga

umu.sePublikationer
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Hierarchical federated transfer learning: a multi-cluster approach on the computing continuum
Vienna University of Technology, Vienna, Austria.
Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. University of Vienna, Vienna, Austria.ORCID-id: 0000-0002-2281-8183
2023 (Engelska)Ingår i: 2023 international conference on machine learning and applications (ICMLA), IEEE, 2023, s. 1163-1168Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

Federated Learning (FL) involves training models over a set of geographically distributed users. We address the problem where a single global model is not enough to meet the needs of geographically distributed heterogeneous clients. This setup captures settings where different groups of users have their own objectives however, users based on geographical location or task similarity, can be grouped together and by inter-cluster knowledge they can leverage the strength in numbers and better generalization in order to perform more efficient FL. We introduce a Hierarchical Multi-Cluster Computing Continuum for Federated Learning Personalization (HC3FL) to cluster similar clients and train one edge model per cluster. HC3FL incorporates federated transfer learning to enhance the performance of edge models by leveraging a global model that captures collective knowledge from all edge models. Furthermore, we introduce dynamic clustering based on task similarity to handle client drift and to dynamically recluster mobile (non-stationary) clients. We evaluate the HC3FL approach through extensive experiments on real-world datasets. The results demonstrate that our approach effectively improves the performance of edge models compared to traditional FL approaches.

Ort, förlag, år, upplaga, sidor
IEEE, 2023. s. 1163-1168
Serie
International Conference on Emerging Technologies and Factory Automation proceedings, ISSN 1946-0740, E-ISSN 1946-0759
Nyckelord [en]
dynamic clustering, federated transfer learning, hierarchical collab-orative learning
Nationell ämneskategori
Datavetenskap (datalogi)
Identifikatorer
URN: urn:nbn:se:umu:diva-223681DOI: 10.1109/ICMLA58977.2023.00174Scopus ID: 2-s2.0-85190111400ISBN: 9798350345346 (digital)ISBN: 9798350318913 (tryckt)OAI: oai:DiVA.org:umu-223681DiVA, id: diva2:1853851
Konferens
22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023, Jacksonville, USA, December 15-17, 2023
Tillgänglig från: 2024-04-23 Skapad: 2024-04-23 Senast uppdaterad: 2024-07-02Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltextScopus

Person

Aral, Atakan

Sök vidare i DiVA

Av författaren/redaktören
Aral, Atakan
Av organisationen
Institutionen för datavetenskap
Datavetenskap (datalogi)

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetricpoäng

doi
isbn
urn-nbn
Totalt: 26 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf