Advances and Open Challenges in Federated Foundation Models

基础(证据) 计算机科学 数据科学 政治学 法学
作者
Chao Ren,Han Yu,Hongyi Peng,Xiaoli Tang,Baihe Zhao,Liping Yi,Alysa Ziying Tan,Yulan Gao,Anran Li,Xiaoxiao Li,Zengxiang Li,Qiang Yang
出处
期刊:IEEE Communications Surveys and Tutorials [Institute of Electrical and Electronics Engineers]
卷期号:28: 2087-2126 被引量:132
标识
DOI:10.1109/comst.2025.3552524
摘要

The integration of Foundation Models (FMs) with Federated Learning (FL) presents a transformative paradigm in Artificial Intelligence (AI). This integration offers enhanced capabilities, while addressing concerns of privacy, data decentralization and computational efficiency. This paper provides a comprehensive survey of the emerging field of Federated Foundation Models (FedFM), elucidating their synergistic relationship and exploring novel methodologies, challenges, and future directions that the FL research field needs to focus on in order to thrive in the age of FMs. A systematic multi-tiered taxonomy is proposed, categorizing existing FedFM approaches for model training, aggregation, trustworthiness, and incentivization. Key challenges, including how to enable FL to deal with high complexity of computational demands, privacy considerations, contribution evaluation, and communication efficiency, are thoroughly discussed. Moreover, this paper explores the intricate challenges of communication, scalability and security inherent in training/fine-tuning FMs via FL. It highlights the potential of quantum computing to revolutionize the processes of training, inference, optimization and security. This survey also introduces the implementation requirement of FedFM and some practical FedFM applications. It highlights lessons learned with a clear understanding of our findings for FedFM. Finally, this survey not only provides insights into the current state and challenges of FedFM, but also offers a blueprint for future research directions, emphasizing the need for developing trustworthy solutions. It serves as a foundational guide for researchers and practitioners interested in contributing to this interdisciplinary and rapidly advancing field.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
CodeCraft的应助被风趣的莞采纳,获得10
刚刚
cff完成签到,获得积分10
1秒前
辉099411发布了新的文献求助10
1秒前
1秒前
1秒前
酷波er的应助被taipingyang采纳,获得10
2秒前
米菲发布了新的文献求助10
2秒前
西原的橙果完成签到,获得积分10
2秒前
Elowen完成签到,获得积分20
3秒前
Jigsaw发布了新的文献求助10
3秒前
tanglu发布了新的文献求助10
3秒前
3秒前
呵呵贺哈完成签到 ,获得积分10
3秒前
4秒前
开放一德发布了新的文献求助10
4秒前
4秒前
Meiyu发布了新的文献求助10
4秒前
syvshc的应助被2206714632采纳,获得10
4秒前
dandelion发布了新的文献求助10
4秒前
想的美发布了新的文献求助10
5秒前
5秒前
开朗灵寒完成签到,获得积分10
6秒前
6秒前
海清河晏完成签到,获得积分10
7秒前
科研通AI6.2的应助被珉志采纳,获得10
8秒前
Akim的应助被朵拉A梦采纳,获得10
8秒前
whistle完成签到,获得积分10
8秒前
Jasper的应助被韦智杰采纳,获得10
9秒前
yuC完成签到,获得积分10
9秒前
梦雅完成签到,获得积分10
9秒前
oioiiio发布了新的文献求助10
9秒前
经十路以东的应助被Meiyu采纳,获得10
10秒前
yy发布了新的文献求助10
10秒前
皮夏寒发布了新的文献求助10
10秒前
10秒前
ding完成签到,获得积分10
11秒前
自然的哈密瓜完成签到,获得积分10
12秒前
13秒前
辉099411完成签到,获得积分10
13秒前
健壮的化蛹完成签到,获得积分10
13秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 2000
Handbook of Sport Coaching Research 1000
Orthognathic Surgery - 2 Volume Set 500
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
基于结构调控的功能化水诱导发电材料与器件研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8194107
求助须知:如何正确求助?哪些是违规求助? 9580062
关于积分的说明 21869017
捐赠科研通 7793713
什么是DOI,文献DOI怎么找? 3437523
关于科研通互助平台的介绍 2560962
邀请新用户注册赠送积分活动 2484264