Sökning: onr:"swepub:oai:DiVA.org:ri-64398" >
Adaptive Expert Mod...
Adaptive Expert Models for Federated Learning
-
- Isaksson, Martin (författare)
- KTH,Programvaruteknik och datorsystem, SCS,Ericsson Res, Stockholm, Sweden,Kungliga Tekniska Högskolan (KTH),Royal Institute of Technology (KTH),Telefonaktiebolaget L M Ericsson,Ericsson
-
- Zec, Edvin Listo (författare)
- KTH,RISE,Datavetenskap,KTH Royal Institute of Technology, Sweden,Programvaruteknik och datorsystem, SCS,RISE Res Inst Sweden, Gothenburg, Sweden.,RISE Research Institutes of Sweden,Kungliga Tekniska Högskolan (KTH),Royal Institute of Technology (KTH)
-
- Cöster, Rickard (författare)
- Ericsson Global AI Accelerator, Stockholm, Sweden.,Telefonaktiebolaget L M Ericsson,Ericsson
-
visa fler...
-
- Gillblad, Daniel, 1975 (författare)
- Chalmers University of Technology, Sweden; AI Sweden, Sweden,Chalmers Univ Technol, Chalmers AI Res Ctr, Gothenburg, Sweden.;AI Sweden, Stockholm, Sweden.,Chalmers tekniska högskola
-
- Girdzijauskas, Sarunas (författare)
- KTH,RISE,Datavetenskap,KTH Royal Institute of Technology, Sweden,Programvaruteknik och datorsystem, SCS,RISE Res Inst Sweden, Stockholm, Sweden.,Kungliga Tekniska Högskolan (KTH),Royal Institute of Technology (KTH),RISE Research Institutes of Sweden
-
visa färre...
-
(creator_code:org_t)
- 2023-03-29
- 2023
- Engelska.
-
Ingår i: <em>Lecture Notes in Computer Science </em>Volume 13448 Pages 1 - 16 2023. - Cham : Springer Science and Business Media Deutschland GmbH. - 9783031289958 ; 13448 LNAI, s. 1-16
- Relaterad länk:
-
https://doi.org/10.1...
-
visa fler...
-
https://urn.kb.se/re...
-
https://doi.org/10.1...
-
https://urn.kb.se/re...
-
https://research.cha...
-
visa färre...
Abstract
Ämnesord
Stäng
- Federated Learning (FL) is a promising framework for distributed learning when data is private and sensitive. However, the state-of-the-art solutions in this framework are not optimal when data is heterogeneous and non-IID. We propose a practical and robust approach to personalization in FL that adjusts to heterogeneous and non-IID data by balancing exploration and exploitation of several global models. To achieve our aim of personalization, we use a Mixture of Experts (MoE) that learns to group clients that are similar to each other, while using the global models more efficiently. We show that our approach achieves an accuracy up to 29.78% better than the state-of-the-art and up to 4.38% better compared to a local model in a pathological non-IID setting, even though we tune our approach in the IID setting. © 2023, The Author(s)
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
- NATURVETENSKAP -- Data- och informationsvetenskap -- Annan data- och informationsvetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Other Computer and Information Science (hsv//eng)
- NATURVETENSKAP -- Data- och informationsvetenskap -- Bioinformatik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Bioinformatics (hsv//eng)
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datorseende och robotik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Vision and Robotics (hsv//eng)
Nyckelord
- Federated learning
- Personalization
- Privacy preserving
- Artificial intelligence
- Learning systems
- Distributed learning
- Expert modeling
- Global models
- Heterogeneous data
- IID data
- Personalizations
- Robust approaches
- State of the art
- Privacy-preserving techniques
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)
Hitta via bibliotek
Till lärosätets databas