Ajou University repository

Can hierarchical client clustering mitigate the data heterogeneity effect in federated learning?
Citations

SCOPUS

0

Citation Export

Publication Year
2023-01-01
Journal
2023 IEEE International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2023
Publisher
Institute of Electrical and Electronics Engineers Inc.
Citation
2023 IEEE International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2023, pp.799-808
Keyword
client clusteringdata heterogeneityfederated learninghierarchical aggregation
Mesh Keyword
Client clusteringClusteringsData heterogeneityFederated learningHeterogeneity effectsHierarchical aggregationNeural network modelPrivacy preservingSingle parameterUser data
All Science Classification Codes (ASJC)
Computer Networks and CommunicationsHardware and Architecture
Abstract
Federated learning (FL) was proposed for training a deep neural network model using millions of user data. The technique has attracted considerable attention owing to its privacy-preserving characteristic. However, two major challenges exist. The first is the limitation of simultaneously participating clients. If the number of clients increases, the single parameter server easily becomes a bottleneck and is prone to have stragglers. The second is data heterogeneity, which adversely affects the accuracy of the global model. Because data should remain at user devices to preserve privacy, we cannot use data shuffling, which is used to homogenize training data in traditional distributed deep learning. We propose a client clustering and model aggregation method, CCFed, to increase the number of simultaneously participating clients and mitigate the data heterogeneity problem. CCFed improves the learning performance using set partition modeling to let data be evenly distributed between clusters and mitigate the effect of a non-IID environment. Experiments show that we can achieve a 2.7-14% higher accuracy using CCFed compared with FedAvg, where CCFed requires approximately 50% less number of rounds compared with FedAvg training on benchmark datasets.
Language
eng
URI
https://aurora.ajou.ac.kr/handle/2018.oak/36969
https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85169297175&origin=inward
DOI
https://doi.org/10.1109/ipdpsw59300.2023.00134
Journal URL
http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=10196463
Type
Conference
Funding
This research was supported by the Korea Insitute of Science and TechnologyInformation(KISTI) (P22010) and by the Basic Science Research Program Through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (2022R1F1A1062779).
Show full item record

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Oh, Sangyoon Image
Oh, Sangyoon오상윤
Department of Software and Computer Engineering
Read More

Total Views & Downloads

File Download

  • There are no files associated with this item.