FedHPL: Efficient Heterogeneous Federated Learning with Prompt Tuning and Logit Distillation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ma, Yuting, Cheng, Lechao, Wang, Yaxiong, Zhong, Zhun, Xu, Xiaohua, Wang, Meng
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929360195289088
author Ma, Yuting
Cheng, Lechao
Wang, Yaxiong
Zhong, Zhun
Xu, Xiaohua
Wang, Meng
author_facet Ma, Yuting
Cheng, Lechao
Wang, Yaxiong
Zhong, Zhun
Xu, Xiaohua
Wang, Meng
contents Federated learning (FL) is a popular privacy-preserving paradigm that enables distributed clients to collaboratively train models with a central server while keeping raw data locally. In practice, distinct model architectures, varying data distributions, and limited resources across local clients inevitably cause model performance degradation and a slowdown in convergence speed. However, existing FL methods can only solve some of the above heterogeneous challenges and have obvious performance limitations. Notably, a unified framework has not yet been explored to overcome these challenges. Accordingly, we propose FedHPL, a parameter-efficient unified $\textbf{Fed}$erated learning framework for $\textbf{H}$eterogeneous settings based on $\textbf{P}$rompt tuning and $\textbf{L}$ogit distillation. Specifically, we employ a local prompt tuning scheme that leverages a few learnable visual prompts to efficiently fine-tune the frozen pre-trained foundation model for downstream tasks, thereby accelerating training and improving model performance under limited local resources and data heterogeneity. Moreover, we design a global logit distillation scheme to handle the model heterogeneity and guide the local training. In detail, we leverage logits to implicitly capture local knowledge and design a weighted knowledge aggregation mechanism to generate global client-specific logits. We provide a theoretical guarantee on the generalization error bound for FedHPL. The experiments on various benchmark datasets under diverse settings of models and data demonstrate that our framework outperforms state-of-the-art FL approaches, with less computation overhead and training rounds.
format Preprint
id arxiv_https___arxiv_org_abs_2405_17267
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FedHPL: Efficient Heterogeneous Federated Learning with Prompt Tuning and Logit Distillation
Ma, Yuting
Cheng, Lechao
Wang, Yaxiong
Zhong, Zhun
Xu, Xiaohua
Wang, Meng
Machine Learning
Computer Vision and Pattern Recognition
Federated learning (FL) is a popular privacy-preserving paradigm that enables distributed clients to collaboratively train models with a central server while keeping raw data locally. In practice, distinct model architectures, varying data distributions, and limited resources across local clients inevitably cause model performance degradation and a slowdown in convergence speed. However, existing FL methods can only solve some of the above heterogeneous challenges and have obvious performance limitations. Notably, a unified framework has not yet been explored to overcome these challenges. Accordingly, we propose FedHPL, a parameter-efficient unified $\textbf{Fed}$erated learning framework for $\textbf{H}$eterogeneous settings based on $\textbf{P}$rompt tuning and $\textbf{L}$ogit distillation. Specifically, we employ a local prompt tuning scheme that leverages a few learnable visual prompts to efficiently fine-tune the frozen pre-trained foundation model for downstream tasks, thereby accelerating training and improving model performance under limited local resources and data heterogeneity. Moreover, we design a global logit distillation scheme to handle the model heterogeneity and guide the local training. In detail, we leverage logits to implicitly capture local knowledge and design a weighted knowledge aggregation mechanism to generate global client-specific logits. We provide a theoretical guarantee on the generalization error bound for FedHPL. The experiments on various benchmark datasets under diverse settings of models and data demonstrate that our framework outperforms state-of-the-art FL approaches, with less computation overhead and training rounds.
title FedHPL: Efficient Heterogeneous Federated Learning with Prompt Tuning and Logit Distillation
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.17267