Sökning: id:"swepub:oai:DiVA.org:liu-190795" >
A New Look and Conv...
A New Look and Convergence Rate of Federated Multitask Learning With Laplacian Regularization
-
- Dinh, Canh T. (författare)
- Univ Sydney, Australia
-
- Vu, Thanh Tung (författare)
- Linköpings universitet,Kommunikationssystem,Tekniska fakulteten
-
- Tran, Nguyen H. (författare)
- Univ Sydney, Australia
-
visa fler...
-
- Dao, Minh N. (författare)
- RMIT Univ, Australia
-
- Zhang, Hongyu (författare)
- Univ Newcastle, Australia
-
visa färre...
-
(creator_code:org_t)
- 2023
- 2023
- Engelska.
-
Ingår i: IEEE Transactions on Neural Networks and Learning Systems. - : IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC. - 2162-237X .- 2162-2388.
- Relaterad länk:
-
https://liu.diva-por... (primary) (Raw object)
-
visa fler...
-
https://urn.kb.se/re...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- Non-independent and identically distributed (non-IID) data distribution among clients is considered as the key factor that degrades the performance of federated learning (FL). Several approaches to handle non-IID data, such as personalized FL and federated multitask learning (FMTL), are of great interest to research communities. In this work, first, we formulate the FMTL problem using Laplacian regularization to explicitly leverage the relationships among the models of clients for multitask learning. Then, we introduce a new view of the FMTL problem, which, for the first time, shows that the formulated FMTL problem can be used for conventional FL and personalized FL. We also propose two algorithms FedU and decentralized FedU (dFedU) to solve the formulated FMTL problem in communication-centralized and decentralized schemes, respectively. Theoretically, we prove that the convergence rates of both algorithms achieve linear speedup for strongly convex and sublinear speedup of order 1/2 for nonconvex objectives. Experimentally, we show that our algorithms outperform the conventional algorithm FedAvg, FedProx, SCAFFOLD, and AFL in FL settings, MOCHA in FMTL settings, as well as pFedMe and Per-FedAvg in personalized FL settings.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Nyckelord
- Federated learning (FL); federated multi-task learning (FMTL); Laplacian regularization; personalized learning
Publikations- och innehållstyp
- ref (ämneskategori)
- art (ämneskategori)
Hitta via bibliotek
Till lärosätets databas