Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ye, Yuchuan, Ding, Ming, Chen, Youjia, Cheng, Peng, Niyato, Dusit
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2601.00526
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909989739692032
author Ye, Yuchuan
Ding, Ming
Chen, Youjia
Cheng, Peng
Niyato, Dusit
author_facet Ye, Yuchuan
Ding, Ming
Chen, Youjia
Cheng, Peng
Niyato, Dusit
contents In this article, we explore federated customization of large models and highlight the key challenges it poses within the federated learning framework. We review several popular large model customization techniques, including full fine-tuning, efficient fine-tuning, prompt engineering, prefix-tuning, knowledge distillation, and retrieval-augmented generation. Then, we discuss how these techniques can be implemented within the federated learning framework. Moreover, we conduct experiments on federated prefix-tuning, which, to the best of our knowledge, is the first trial to apply prefix-tuning in the federated learning setting. The conducted experiments validate its feasibility with performance close to centralized approaches. Further comparison with three other federated customization methods demonstrated its competitive performance, satisfactory efficiency, and consistent robustness.
format Preprint
id arxiv_https___arxiv_org_abs_2601_00526
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Federated Customization of Large Models: Approaches, Experiments, and Insights
Ye, Yuchuan
Ding, Ming
Chen, Youjia
Cheng, Peng
Niyato, Dusit
Machine Learning
Distributed, Parallel, and Cluster Computing
In this article, we explore federated customization of large models and highlight the key challenges it poses within the federated learning framework. We review several popular large model customization techniques, including full fine-tuning, efficient fine-tuning, prompt engineering, prefix-tuning, knowledge distillation, and retrieval-augmented generation. Then, we discuss how these techniques can be implemented within the federated learning framework. Moreover, we conduct experiments on federated prefix-tuning, which, to the best of our knowledge, is the first trial to apply prefix-tuning in the federated learning setting. The conducted experiments validate its feasibility with performance close to centralized approaches. Further comparison with three other federated customization methods demonstrated its competitive performance, satisfactory efficiency, and consistent robustness.
title Federated Customization of Large Models: Approaches, Experiments, and Insights
topic Machine Learning
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2601.00526