University of Aberdeen logo

AURA - Aberdeen University Research Archive

 

Accelerate Training of Personalised Multi-Task Federated Learning

dc.contributor.authorLi, Yiren
dc.contributor.authorSharma, Pradip
dc.contributor.authorLeontidis, Georgios
dc.contributor.authorYi, Dewei
dc.contributor.institutionUniversity of Aberdeen.Natural & Computing Sciencesen
dc.contributor.institutionUniversity of Aberdeen.Computing Scienceen
dc.date.accessioned2024-12-16T13:38:05Z
dc.date.available2024-12-16T13:38:05Z
dc.date.issued2024-10-23
dc.format.extent6
dc.format.extent18700528
dc.identifier298911956
dc.identifier316e4e00-b555-48b1-bfb5-b6696c10516b
dc.identifier85208652782
dc.identifier85208652782
dc.identifier.citationLi, Y, Sharma, P, Leontidis, G & Yi, D 2024, Accelerate Training of Personalised Multi-Task Federated Learning. in Proceedings: 2024 29th International Conference on Automation and Computing (ICAC). IEEE Explore, The 29th International Conference on Automation and Computing, Sunderland, United Kingdom, 28/08/24. https://doi.org/10.1109/ICAC61394.2024.10718836en
dc.identifier.citationconferenceen
dc.identifier.doi10.1109/ICAC61394.2024.10718836
dc.identifier.isbn979-8-3503-6089-9
dc.identifier.isbn979-8-3503-6088-2
dc.identifier.otherORCID: /0000-0001-6671-5568/work/173887254
dc.identifier.otherORCID: /0000-0001-6620-9083/work/173887307
dc.identifier.otherORCID: /0000-0003-1702-9136/work/173887495
dc.identifier.urihttps://hdl.handle.net/2164/24767
dc.identifier.urlhttp://www.scopus.com/inward/record.url?scp=85208652782&partnerID=8YFLogxKen
dc.language.isoeng
dc.publisherIEEE Explore
dc.relation.ispartofProceedings: 2024 29th International Conference on Automation and Computing (ICAC)en
dc.subjectQA75 Electronic computers. Computer scienceen
dc.subject.lccQA75en
dc.titleAccelerate Training of Personalised Multi-Task Federated Learningen
dc.typeConference itemen

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
Li_etal_ICAC_Accelerate_Training_Of_AAM.pdf
Size:
17.83 MB
Format:
Adobe Portable Document Format

Collections