Please use this identifier to cite or link to this item: https://elib.vku.udn.vn/handle/123456789/3988
Title: Contrastive encoder pre-training-based clustered federated learning for heterogeneous data
Authors: Tun, Ye Lin
Nguyen, Huu Nhat Minh
Thwal, Chu Myaet
Choi, Jinwoo
Keywords: Federated learning
data heterogeneity
contrastive learning
unlabeled data
Issue Date: Aug-2023
Publisher: Elsevier Ltd
Abstract: Federated learning (FL) is a promising approach that enables distributed clients to collaboratively train a global model while preserving their data privacy. However, FL often suffers from data heterogeneity problems, which can significantly affect its performance. To address this, clustered federated learning (CFL) has been proposed to construct personalized models for different client clusters. One effective client clustering strategy is to allow clients to choose their own local models from a model pool based on their performance. However, without pre-trained model parameters, such a strategy is prone to clustering failure, in which all clients choose the same model. Unfortunately, collecting a large amount of labeled data for pre-training can be costly and impractical in distributed environments. To overcome this challenge, we leverage self-supervised contrastive learning to exploit unlabeled data for the pre-training of FL systems. Together, self-supervised pre-training and client clustering can be crucial components for tackling the data heterogeneity issues of FL. Leveraging these two crucial strategies, we propose contrastive pre-training-based clustered federated learning (CP-CFL) to improve the model convergence and overall performance of FL systems. In this work, we demonstrate the effectiveness of CP-CFL through extensive experiments in heterogeneous FL settings, and present various interesting observations.
Description: Neural Networks 165 (2023); pp: 689-704
URI: https://doi.org/10.1016/j.neunet.2023.06.010
https://elib.vku.udn.vn/handle/123456789/3988
Appears in Collections:NĂM 2023

Files in This Item:

 Sign in to read



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