Personalized Decentralized Federated Learning with Knowledge Distillation

被引:1
|
作者
Jeong, Eunjeong [1 ]
Kountouris, Marios [1 ]
机构
[1] EURECOM, Commun Syst Dept, F-06410 Sophia Antipolis, France
关键词
decentralized federated learning; personalization; knowledge distillation;
D O I
10.1109/ICC45041.2023.10279714
中图分类号
TN [电子技术、通信技术];
学科分类号
0809 ;
摘要
Personalization in federated learning (FL) functions as a coordinator for clients with high variance in data or behavior. Ensuring the convergence of these clients' models relies on how closely users collaborate with those with similar patterns or preferences. However, it is generally challenging to quantify similarity under limited knowledge about other users' models given to users in a decentralized network. To cope with this issue, we propose a personalized and fully decentralized FL algorithm, leveraging knowledge distillation techniques to empower each device so as to discern statistical distances between local models. Each client device can enhance its performance without sharing local data by estimating the similarity between two intermediate outputs from feeding local samples as in knowledge distillation. Our empirical studies demonstrate that the proposed algorithm improves the test accuracy of clients in fewer iterations under highly non-independent and identically distributed (non-i.i.d.) data distributions and is beneficial to agents with small datasets, even without the need for a central server.
引用
收藏
页码:1982 / 1987
页数:6
相关论文
共 50 条
  • [1] FedDKD: Federated learning with decentralized knowledge distillation
    Li, Xinjia
    Chen, Boyu
    Lu, Wenlian
    APPLIED INTELLIGENCE, 2023, 53 (15) : 18547 - 18563
  • [2] FedDKD: Federated learning with decentralized knowledge distillation
    Xinjia Li
    Boyu Chen
    Wenlian Lu
    Applied Intelligence, 2023, 53 : 18547 - 18563
  • [3] DECENTRALIZED FEDERATED LEARNING VIA MUTUAL KNOWLEDGE DISTILLATION
    Huang, Yue
    Kong, Lanju
    Li, Qingzhong
    Zhang, Baochen
    2023 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, ICME, 2023, : 342 - 347
  • [4] A Decentralized Federated Learning Based on Node Selection and Knowledge Distillation
    Zhou, Zhongchang
    Sun, Fenggang
    Chen, Xiangyu
    Zhang, Dongxu
    Han, Tianzhen
    Lan, Peng
    MATHEMATICS, 2023, 11 (14)
  • [5] A Personalized Federated Learning Method Based on Clustering and Knowledge Distillation
    Zhang, Jianfei
    Shi, Yongqiang
    ELECTRONICS, 2024, 13 (05)
  • [6] A Personalized Federated Learning Algorithm Based on Meta-Learning and Knowledge Distillation
    Sun Y.
    Shi Y.
    Wang Z.
    Li M.
    Si P.
    Beijing Youdian Daxue Xuebao/Journal of Beijing University of Posts and Telecommunications, 2023, 46 (01): : 12 - 18
  • [7] FedDK: Improving Cyclic Knowledge Distillation for Personalized Healthcare Federated Learning
    Xu, Yikai
    Fan, Hongbo
    IEEE ACCESS, 2023, 11 : 72409 - 72417
  • [8] A Personalized Federated Learning Method Based on Knowledge Distillation and Differential Privacy
    Jiang, Yingrui
    Zhao, Xuejian
    Li, Hao
    Xue, Yu
    ELECTRONICS, 2024, 13 (17)
  • [9] Personalized Federated Learning Method Based on Collation Game and Knowledge Distillation
    Sun Y.
    Shi Y.
    Li M.
    Yang R.
    Si P.
    Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology, 2023, 45 (10): : 3702 - 3709
  • [10] Personalized Federated Learning with Semisupervised Distillation
    Li, Xianxian
    Gong, Yanxia
    Liang, Yuan
    Wang, Li-e
    SECURITY AND COMMUNICATION NETWORKS, 2021, 2021