FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extraction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Feijie, Wang, Xingchen, Wang, Yaqing, Liu, Tianci, Su, Lu, Gao, Jing
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916513709031424
author Wu, Feijie
Wang, Xingchen
Wang, Yaqing
Liu, Tianci
Su, Lu
Gao, Jing
author_facet Wu, Feijie
Wang, Xingchen
Wang, Yaqing
Liu, Tianci
Su, Lu
Gao, Jing
contents In federated learning (FL), accommodating clients' varied computational capacities poses a challenge, often limiting the participation of those with constrained resources in global model training. To address this issue, the concept of model heterogeneity through submodel extraction has emerged, offering a tailored solution that aligns the model's complexity with each client's computational capacity. In this work, we propose Federated Importance-Aware Submodel Extraction (FIARSE), a novel approach that dynamically adjusts submodels based on the importance of model parameters, thereby overcoming the limitations of previous static and dynamic submodel extraction methods. Compared to existing works, the proposed method offers a theoretical foundation for the submodel extraction and eliminates the need for additional information beyond the model parameters themselves to determine parameter importance, significantly reducing the overhead on clients. Extensive experiments are conducted on various datasets to showcase the superior performance of the proposed FIARSE.
format Preprint
id arxiv_https___arxiv_org_abs_2407_19389
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extraction
Wu, Feijie
Wang, Xingchen
Wang, Yaqing
Liu, Tianci
Su, Lu
Gao, Jing
Distributed, Parallel, and Cluster Computing
Machine Learning
Optimization and Control
In federated learning (FL), accommodating clients' varied computational capacities poses a challenge, often limiting the participation of those with constrained resources in global model training. To address this issue, the concept of model heterogeneity through submodel extraction has emerged, offering a tailored solution that aligns the model's complexity with each client's computational capacity. In this work, we propose Federated Importance-Aware Submodel Extraction (FIARSE), a novel approach that dynamically adjusts submodels based on the importance of model parameters, thereby overcoming the limitations of previous static and dynamic submodel extraction methods. Compared to existing works, the proposed method offers a theoretical foundation for the submodel extraction and eliminates the need for additional information beyond the model parameters themselves to determine parameter importance, significantly reducing the overhead on clients. Extensive experiments are conducted on various datasets to showcase the superior performance of the proposed FIARSE.
title FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extraction
topic Distributed, Parallel, and Cluster Computing
Machine Learning
Optimization and Control
url https://arxiv.org/abs/2407.19389