Enregistré dans:
Détails bibliographiques
Auteurs principaux: Li, Shenghui, Ye, Fanghua, Fang, Meng, Zhao, Jiaxu, Chan, Yun-Hin, Ngai, Edith C. H., Voigt, Thiemo
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2406.12844
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914332107866112
author Li, Shenghui
Ye, Fanghua
Fang, Meng
Zhao, Jiaxu
Chan, Yun-Hin
Ngai, Edith C. H.
Voigt, Thiemo
author_facet Li, Shenghui
Ye, Fanghua
Fang, Meng
Zhao, Jiaxu
Chan, Yun-Hin
Ngai, Edith C. H.
Voigt, Thiemo
contents Over the past few years, the landscape of Artificial Intelligence (AI) has been reshaped by the emergence of Foundation Models (FMs). Pre-trained on massive datasets, these models exhibit exceptional performance across diverse downstream tasks through adaptation techniques like fine-tuning and prompt learning. More recently, the synergy of FMs and Federated Learning (FL) has emerged as a promising paradigm, often termed Federated Foundation Models (FedFM), allowing for collaborative model adaptation while preserving data privacy. This survey paper provides a systematic review of the current state of the art in FedFM, offering insights and guidance into the evolving landscape. Specifically, we present a comprehensive multi-tiered taxonomy based on three major dimensions, namely efficiency, adaptability, and trustworthiness. To facilitate practical implementation and experimental research, we undertake a thorough review of existing libraries and benchmarks. Furthermore, we discuss the diverse real-world applications of this paradigm across multiple domains. Finally, we outline promising research directions to foster future advancements in FedFM. Overall, this survey serves as a resource for researchers and practitioners, offering a thorough understanding of FedFM's role in revolutionizing privacy-preserving AI and pointing toward future innovations in this promising area. A periodically updated paper collection on FM-FL is available at https://github.com/lishenghui/awesome-fm-fl.
format Preprint
id arxiv_https___arxiv_org_abs_2406_12844
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Synergizing Foundation Models and Federated Learning: A Survey
Li, Shenghui
Ye, Fanghua
Fang, Meng
Zhao, Jiaxu
Chan, Yun-Hin
Ngai, Edith C. H.
Voigt, Thiemo
Machine Learning
Artificial Intelligence
Over the past few years, the landscape of Artificial Intelligence (AI) has been reshaped by the emergence of Foundation Models (FMs). Pre-trained on massive datasets, these models exhibit exceptional performance across diverse downstream tasks through adaptation techniques like fine-tuning and prompt learning. More recently, the synergy of FMs and Federated Learning (FL) has emerged as a promising paradigm, often termed Federated Foundation Models (FedFM), allowing for collaborative model adaptation while preserving data privacy. This survey paper provides a systematic review of the current state of the art in FedFM, offering insights and guidance into the evolving landscape. Specifically, we present a comprehensive multi-tiered taxonomy based on three major dimensions, namely efficiency, adaptability, and trustworthiness. To facilitate practical implementation and experimental research, we undertake a thorough review of existing libraries and benchmarks. Furthermore, we discuss the diverse real-world applications of this paradigm across multiple domains. Finally, we outline promising research directions to foster future advancements in FedFM. Overall, this survey serves as a resource for researchers and practitioners, offering a thorough understanding of FedFM's role in revolutionizing privacy-preserving AI and pointing toward future innovations in this promising area. A periodically updated paper collection on FM-FL is available at https://github.com/lishenghui/awesome-fm-fl.
title Synergizing Foundation Models and Federated Learning: A Survey
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2406.12844