Personalized Federated Learning Method Based on Collation Game and Knowledge Distillation; [基于合作博弈和知识蒸馏的个性化联邦学习算法] - Details

Author：

Sun, Y. (Sun, Y..) | Shi, Y. (Shi, Y..) | Li, M. (Li, M..) | Yang, R. (Yang, R..) | Si, P. (Si, P..)

Indexed by：

EI Scopus

Abstract：

To　overcome　the　limitation　of　the　Federated　Learning　(FL)　when　the　data　and　model　of　each　client　are　all　heterogenous　and　improve　the　accuracy,　a　personalized　Federated　learning　algorithm　with　Collation　game　and　Knowledge　distillation　(pFedCK)　is　proposed.　Firstly,　each　client　uploads　its　soft-predict　on　public　dataset　and　downloads　the　most　correlative　of　the　k　soft-predict.　Then,　the　Shapley　Value　(SV)　from　collation　game　is　applied　to　measure　the　multi-wise　influences　among　clients　and　their　marginal　contribution　to　others　on　personalized　learning　performance　is　quantified.　Lastly,　each　client　identify　it’s　optimal　coalition　and　then　the　Knowledge　Distillation　(KD)　is　used　to　local　model　and　local　training　is　conduct　on　the　privacy　dataset.　The　results　show　that　compared　with　the　state-of-the-art　algorithm,　this　approach　can　achieve　superior　personalized　accuracy　and　can　improve　by　about　10%.　©　2023　Science　Press.　All　rights　reserved.

Keyword：

Knowledge Distillation (KD) Personalized Federated Learning(PFL) Heterogeneity Collation game

Author Community：

[ 1 ] [Sun Y.]Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China) (Beijing Laboratory of Advanced Information Networks, Beijing University of Technology, Beijing 100124, China)
[ 2 ] [Shi Y.]Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China) (Beijing Laboratory of Advanced Information Networks, Beijing University of Technology, Beijing 100124, China)
[ 3 ] [Li M.]Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China) (Beijing Laboratory of Advanced Information Networks, Beijing University of Technology, Beijing 100124, China)
[ 4 ] [Yang R.]Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China) (Beijing Laboratory of Advanced Information Networks, Beijing University of Technology, Beijing 100124, China)
[ 5 ] [Si P.]Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China) (Beijing Laboratory of Advanced Information Networks, Beijing University of Technology, Beijing 100124, China)

Reprint Author's Address：

Email：

Show more details

Related Keywords：

Methods and Prospects of Personalized Federated Learning
2024，Computer Engineering and Applications
Model optimization techniques in personalized federated learning: A survey
2023，EXPERT SYSTEMS WITH APPLICATIONS
Communication optimization techniques in Personalized Federated Learning: Applications, challenges and future directions
2025，INFORMATION FUSION
Convergence-Privacy-Fairness Trade-Off in Personalized Federated Learning
2025，IEEE Transactions on Machine Learning in Communications and Networking

Source ：

Journal of Electronics and Information Technology

ISSN： 1009-5896

Year： 2023

Issue： 10

Volume： 45

Page： 3702-3709

Cited Count：

WoS CC Cited Count： 0

SCOPUS Cited Count： 1

ESI Highly Cited Papers on the List： 0 Unfold All

WanFang Cited Count：

Chinese Cited Count：

30 Days PV： 22

Affiliated Colleges：

Get Fulltext

DOI Library Discovery Baidu Scholar Search SCOPUS

Type
Departments

All Years Choose Year From to