Personalized federated learning based on feature fusion

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Xing, Wolong, Shi, Zhenkui, Peng, Hongyan, Hu, Xiantao, Li, Xianxian
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917703417069568
author Xing, Wolong
Shi, Zhenkui
Peng, Hongyan
Hu, Xiantao
Li, Xianxian
author_facet Xing, Wolong
Shi, Zhenkui
Peng, Hongyan
Hu, Xiantao
Li, Xianxian
contents Federated learning enables distributed clients to collaborate on training while storing their data locally to protect client privacy. However, due to the heterogeneity of data, models, and devices, the final global model may need to perform better for tasks on each client. Communication bottlenecks, data heterogeneity, and model heterogeneity have been common challenges in federated learning. In this work, we considered a label distribution skew problem, a type of data heterogeneity easily overlooked. In the context of classification, we propose a personalized federated learning approach called pFedPM. In our process, we replace traditional gradient uploading with feature uploading, which helps reduce communication costs and allows for heterogeneous client models. These feature representations play a role in preserving privacy to some extent. We use a hyperparameter $a$ to mix local and global features, which enables us to control the degree of personalization. We also introduced a relation network as an additional decision layer, which provides a non-linear learnable classifier to predict labels. Experimental results show that, with an appropriate setting of $a$, our scheme outperforms several recent FL methods on MNIST, FEMNIST, and CRIFAR10 datasets and achieves fewer communications.
format Preprint
id arxiv_https___arxiv_org_abs_2406_16583
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Personalized federated learning based on feature fusion
Xing, Wolong
Shi, Zhenkui
Peng, Hongyan
Hu, Xiantao
Li, Xianxian
Machine Learning
Computer Vision and Pattern Recognition
Federated learning enables distributed clients to collaborate on training while storing their data locally to protect client privacy. However, due to the heterogeneity of data, models, and devices, the final global model may need to perform better for tasks on each client. Communication bottlenecks, data heterogeneity, and model heterogeneity have been common challenges in federated learning. In this work, we considered a label distribution skew problem, a type of data heterogeneity easily overlooked. In the context of classification, we propose a personalized federated learning approach called pFedPM. In our process, we replace traditional gradient uploading with feature uploading, which helps reduce communication costs and allows for heterogeneous client models. These feature representations play a role in preserving privacy to some extent. We use a hyperparameter $a$ to mix local and global features, which enables us to control the degree of personalization. We also introduced a relation network as an additional decision layer, which provides a non-linear learnable classifier to predict labels. Experimental results show that, with an appropriate setting of $a$, our scheme outperforms several recent FL methods on MNIST, FEMNIST, and CRIFAR10 datasets and achieves fewer communications.
title Personalized federated learning based on feature fusion
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.16583