FedFMSL: Federated Learning of Foundation Models With Sparsely Activated LoRA

IF 7.7 2区 计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS IEEE Transactions on Mobile Computing Pub Date : 2024-09-04 DOI:10.1109/TMC.2024.3454634
Panlong Wu;Kangshuo Li;Ting Wang;Yanjie Dong;Victor C. M. Leung;Fangxin Wang
{"title":"FedFMSL: Federated Learning of Foundation Models With Sparsely Activated LoRA","authors":"Panlong Wu;Kangshuo Li;Ting Wang;Yanjie Dong;Victor C. M. Leung;Fangxin Wang","doi":"10.1109/TMC.2024.3454634","DOIUrl":null,"url":null,"abstract":"Foundation models (FMs) have shown great success in natural language processing, computer vision, and multimodal tasks. FMs have a large number of model parameters, thus requiring a substantial amount of data to help optimize the model during the training. Federated learning has revolutionized machine learning by enabling collaborative learning from decentralized data while still preserving clients’ data privacy. Despite the great benefits foundation models can have empowered by federated learning, their bulky model parameters cause severe communication challenges for modern networks and computation challenges especially for edge devices. Moreover, the data distribution of different clients can be different thus inducing statistical challenges. In this paper, we propose a novel two-stage federated learning algorithm called FedFMSL. A global expert is trained in the first stage and a local expert is trained in the second stage to provide better personalization. We construct a Mixture of Foundation Models (\n<monospace>MoFM</monospace>\n) with these two experts and design a gate neural network with an inserted gate adapter that joins the aggregation every communication round in the second stage. To further adapt to edge computing scenarios with limited computational resources, we design a novel Sparsely Activated LoRA (\n<monospace>SAL</monospace>\n) algorithm that freezes the pre-trained foundation model parameters inserts low-rank adaptation matrices into transformer blocks, and activates them progressively during the training. We employ extensive experiments to verify the effectiveness of FedFMSL, results show that FedFMSL outperforms other SOTA baselines by up to 59.19% in default settings while tuning less than 0.3% parameters of the foundation model.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":null,"pages":null},"PeriodicalIF":7.7000,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Mobile Computing","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10666083/","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0

Abstract

Foundation models (FMs) have shown great success in natural language processing, computer vision, and multimodal tasks. FMs have a large number of model parameters, thus requiring a substantial amount of data to help optimize the model during the training. Federated learning has revolutionized machine learning by enabling collaborative learning from decentralized data while still preserving clients’ data privacy. Despite the great benefits foundation models can have empowered by federated learning, their bulky model parameters cause severe communication challenges for modern networks and computation challenges especially for edge devices. Moreover, the data distribution of different clients can be different thus inducing statistical challenges. In this paper, we propose a novel two-stage federated learning algorithm called FedFMSL. A global expert is trained in the first stage and a local expert is trained in the second stage to provide better personalization. We construct a Mixture of Foundation Models ( MoFM ) with these two experts and design a gate neural network with an inserted gate adapter that joins the aggregation every communication round in the second stage. To further adapt to edge computing scenarios with limited computational resources, we design a novel Sparsely Activated LoRA ( SAL ) algorithm that freezes the pre-trained foundation model parameters inserts low-rank adaptation matrices into transformer blocks, and activates them progressively during the training. We employ extensive experiments to verify the effectiveness of FedFMSL, results show that FedFMSL outperforms other SOTA baselines by up to 59.19% in default settings while tuning less than 0.3% parameters of the foundation model.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
FedFMSL:利用稀疏激活的 LoRA 联合学习基础模型
基础模型(FM)在自然语言处理、计算机视觉和多模态任务中取得了巨大成功。FM 有大量的模型参数,因此需要大量数据来帮助在训练过程中优化模型。联盟学习使机器学习发生了革命性的变化,它可以从分散的数据中进行协作学习,同时还能保护客户的数据隐私。尽管联合学习能为基础模型带来巨大好处,但其庞大的模型参数会给现代网络带来严峻的通信挑战,尤其是给边缘设备的计算带来挑战。此外,不同客户的数据分布也可能不同,从而带来统计方面的挑战。在本文中,我们提出了一种名为 FedFMSL 的新型两阶段联合学习算法。第一阶段训练全局专家,第二阶段训练本地专家,以提供更好的个性化服务。我们用这两位专家构建了一个基础模型混合物(MoFM),并设计了一个带有插入式门适配器的门神经网络,该适配器在第二阶段的每一轮通信中都会加入聚合。为了进一步适应计算资源有限的边缘计算场景,我们设计了一种新颖的稀疏激活 LoRA(SAL)算法,它可以冻结预先训练好的基础模型参数,将低秩适应矩阵插入变压器块,并在训练过程中逐步激活它们。我们通过大量实验来验证 FedFMSL 的有效性,结果表明,在默认设置下,FedFMSL 的性能比其他 SOTA 基线高出 59.19%,而基础模型参数的调整率不到 0.3%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
IEEE Transactions on Mobile Computing
IEEE Transactions on Mobile Computing 工程技术-电信学
CiteScore
12.90
自引率
2.50%
发文量
403
审稿时长
6.6 months
期刊介绍: IEEE Transactions on Mobile Computing addresses key technical issues related to various aspects of mobile computing. This includes (a) architectures, (b) support services, (c) algorithm/protocol design and analysis, (d) mobile environments, (e) mobile communication systems, (f) applications, and (g) emerging technologies. Topics of interest span a wide range, covering aspects like mobile networks and hosts, mobility management, multimedia, operating system support, power management, online and mobile environments, security, scalability, reliability, and emerging technologies such as wearable computers, body area networks, and wireless sensor networks. The journal serves as a comprehensive platform for advancements in mobile computing research.
期刊最新文献
Charger Placement with Wave Interference t-READi: Transformer-Powered Robust and Efficient Multimodal Inference for Autonomous Driving Exploitation and Confrontation: Sustainability Analysis of Crowdsourcing Bison : A Binary Sparse Network Coding based Contents Sharing Scheme for D2D-Enabled Mobile Edge Caching Network Argus: Enabling Cross-Camera Collaboration for Video Analytics on Distributed Smart Cameras
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1