FedReMa: Improving Personalized Federated Learning via Leveraging the Most Relevant Clients

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Liang, Han, Zhan, Ziwei, Liu, Weijie, Zhang, Xiaoxi, Tan, Chee Wei, Chen, Xu
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917848603951104
author Liang, Han
Zhan, Ziwei
Liu, Weijie
Zhang, Xiaoxi
Tan, Chee Wei
Chen, Xu
author_facet Liang, Han
Zhan, Ziwei
Liu, Weijie
Zhang, Xiaoxi
Tan, Chee Wei
Chen, Xu
contents Federated Learning (FL) is a distributed machine learning paradigm that achieves a globally robust model through decentralized computation and periodic model synthesis, primarily focusing on the global model's accuracy over aggregated datasets of all participating clients. Personalized Federated Learning (PFL) instead tailors exclusive models for each client, aiming to enhance the accuracy of clients' individual models on specific local data distributions. Despite of their wide adoption, existing FL and PFL works have yet to comprehensively address the class-imbalance issue, one of the most critical challenges within the realm of data heterogeneity in PFL and FL research. In this paper, we propose FedReMa, an efficient PFL algorithm that can tackle class-imbalance by 1) utilizing an adaptive inter-client co-learning approach to identify and harness different clients' expertise on different data classes throughout various phases of the training process, and 2) employing distinct aggregation methods for clients' feature extractors and classifiers, with the choices informed by the different roles and implications of these model components. Specifically, driven by our experimental findings on inter-client similarity dynamics, we develop critical co-learning period (CCP), wherein we introduce a module named maximum difference segmentation (MDS) to assess and manage task relevance by analyzing the similarities between clients' logits of their classifiers. Outside the CCP, we employ an additional scheme for model aggregation that utilizes historical records of each client's most relevant peers to further enhance the personalization stability. We demonstrate the superiority of our FedReMa in extensive experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2411_01825
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FedReMa: Improving Personalized Federated Learning via Leveraging the Most Relevant Clients
Liang, Han
Zhan, Ziwei
Liu, Weijie
Zhang, Xiaoxi
Tan, Chee Wei
Chen, Xu
Machine Learning
Distributed, Parallel, and Cluster Computing
Federated Learning (FL) is a distributed machine learning paradigm that achieves a globally robust model through decentralized computation and periodic model synthesis, primarily focusing on the global model's accuracy over aggregated datasets of all participating clients. Personalized Federated Learning (PFL) instead tailors exclusive models for each client, aiming to enhance the accuracy of clients' individual models on specific local data distributions. Despite of their wide adoption, existing FL and PFL works have yet to comprehensively address the class-imbalance issue, one of the most critical challenges within the realm of data heterogeneity in PFL and FL research. In this paper, we propose FedReMa, an efficient PFL algorithm that can tackle class-imbalance by 1) utilizing an adaptive inter-client co-learning approach to identify and harness different clients' expertise on different data classes throughout various phases of the training process, and 2) employing distinct aggregation methods for clients' feature extractors and classifiers, with the choices informed by the different roles and implications of these model components. Specifically, driven by our experimental findings on inter-client similarity dynamics, we develop critical co-learning period (CCP), wherein we introduce a module named maximum difference segmentation (MDS) to assess and manage task relevance by analyzing the similarities between clients' logits of their classifiers. Outside the CCP, we employ an additional scheme for model aggregation that utilizes historical records of each client's most relevant peers to further enhance the personalization stability. We demonstrate the superiority of our FedReMa in extensive experiments.
title FedReMa: Improving Personalized Federated Learning via Leveraging the Most Relevant Clients
topic Machine Learning
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2411.01825