资源受限物联网系统的动态分裂联邦学习

IF 4.3 3区 计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS
Mohamad Wazzeh , Ahmad Hammoud , Azzam Mourad , Hadi Otrok , Chamseddine Talhi , Zbigniew Dziong , Chang-Dong Wang , Mohsen Guizani
{"title":"资源受限物联网系统的动态分裂联邦学习","authors":"Mohamad Wazzeh ,&nbsp;Ahmad Hammoud ,&nbsp;Azzam Mourad ,&nbsp;Hadi Otrok ,&nbsp;Chamseddine Talhi ,&nbsp;Zbigniew Dziong ,&nbsp;Chang-Dong Wang ,&nbsp;Mohsen Guizani","doi":"10.1016/j.comcom.2025.108275","DOIUrl":null,"url":null,"abstract":"<div><div>Efficient resource utilization in Internet of Things (IoT) systems is challenging due to device limitations. These limitations restrict on-device machine learning (ML) model training, leading to longer processing times and inefficient metadata analysis. Additionally, conventional centralized data collection poses privacy concerns, as raw data has to leave the device to the server for processing. Combining Federated Learning (FL) and Split Learning (SL) offers a promising solution by enabling effective machine learning on resource-constrained devices while preserving user privacy. However, the dynamic nature of IoT resources and device heterogeneity can complicate the application of these solutions, as some IoT devices cannot complete the training task on time. To address these concerns, we have developed a Dynamic Split Federated Learning (DSFL) architecture that dynamically adjusts to the real-time resource availability of individual clients. Combining real-time split-point selection with a Genetic Algorithm (GA) for client selection, tailored to heterogeneous, resource-constrained IoT devices. DSFL ensures optimal utilization of resources and efficient training across heterogeneous IoT devices and servers. Our architecture detects each IoT device’s training capabilities by identifying the number of layers it can train. Moreover, an effective Genetic Algorithm (GA) process strategically selects the clients required to complete the split federated learning round. Cooperatively, the clients and servers train their parts of the model, aggregate them, and then combine the results before moving to the next round. Our proposed architecture enables collaborative model training across devices while preserving data privacy by combining FL’s parallelism with SL’s dynamic modeling. We evaluated our architecture on sensory and image-based datasets, showing improved accuracy and reduced overhead compared to baseline methods.</div></div>","PeriodicalId":55224,"journal":{"name":"Computer Communications","volume":"242 ","pages":"Article 108275"},"PeriodicalIF":4.3000,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Dynamic Split Federated Learning for resource-constrained IoT systems\",\"authors\":\"Mohamad Wazzeh ,&nbsp;Ahmad Hammoud ,&nbsp;Azzam Mourad ,&nbsp;Hadi Otrok ,&nbsp;Chamseddine Talhi ,&nbsp;Zbigniew Dziong ,&nbsp;Chang-Dong Wang ,&nbsp;Mohsen Guizani\",\"doi\":\"10.1016/j.comcom.2025.108275\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Efficient resource utilization in Internet of Things (IoT) systems is challenging due to device limitations. These limitations restrict on-device machine learning (ML) model training, leading to longer processing times and inefficient metadata analysis. Additionally, conventional centralized data collection poses privacy concerns, as raw data has to leave the device to the server for processing. Combining Federated Learning (FL) and Split Learning (SL) offers a promising solution by enabling effective machine learning on resource-constrained devices while preserving user privacy. However, the dynamic nature of IoT resources and device heterogeneity can complicate the application of these solutions, as some IoT devices cannot complete the training task on time. To address these concerns, we have developed a Dynamic Split Federated Learning (DSFL) architecture that dynamically adjusts to the real-time resource availability of individual clients. Combining real-time split-point selection with a Genetic Algorithm (GA) for client selection, tailored to heterogeneous, resource-constrained IoT devices. DSFL ensures optimal utilization of resources and efficient training across heterogeneous IoT devices and servers. Our architecture detects each IoT device’s training capabilities by identifying the number of layers it can train. Moreover, an effective Genetic Algorithm (GA) process strategically selects the clients required to complete the split federated learning round. Cooperatively, the clients and servers train their parts of the model, aggregate them, and then combine the results before moving to the next round. Our proposed architecture enables collaborative model training across devices while preserving data privacy by combining FL’s parallelism with SL’s dynamic modeling. We evaluated our architecture on sensory and image-based datasets, showing improved accuracy and reduced overhead compared to baseline methods.</div></div>\",\"PeriodicalId\":55224,\"journal\":{\"name\":\"Computer Communications\",\"volume\":\"242 \",\"pages\":\"Article 108275\"},\"PeriodicalIF\":4.3000,\"publicationDate\":\"2025-07-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Computer Communications\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0140366425002324\",\"RegionNum\":3,\"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}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer Communications","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0140366425002324","RegionNum":3,"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

摘要

由于设备的限制,物联网(IoT)系统的有效资源利用具有挑战性。这些限制限制了设备上机器学习(ML)模型训练,导致处理时间更长,元数据分析效率低下。此外,传统的集中式数据收集会带来隐私问题,因为原始数据必须将设备留给服务器进行处理。结合联邦学习(FL)和分裂学习(SL)提供了一种有前途的解决方案,可以在资源受限的设备上实现有效的机器学习,同时保护用户隐私。然而,物联网资源的动态性和设备的异质性会使这些解决方案的应用复杂化,因为一些物联网设备无法按时完成培训任务。为了解决这些问题,我们开发了一个动态分离联邦学习(DSFL)体系结构,它可以动态地调整单个客户机的实时资源可用性。结合实时分离点选择和用于客户端选择的遗传算法(GA),为异构,资源受限的物联网设备量身定制。DSFL确保资源的最佳利用和跨异构物联网设备和服务器的高效培训。我们的架构通过识别可以训练的层数来检测每个物联网设备的训练能力。此外,一个有效的遗传算法(GA)过程策略性地选择完成分裂联邦学习轮所需的客户端。客户端和服务器协同训练模型的各自部分,聚合它们,然后在进入下一轮之前组合结果。我们提出的架构支持跨设备的协作模型训练,同时通过将FL的并行性与SL的动态建模相结合来保护数据隐私。我们在感官和基于图像的数据集上评估了我们的架构,与基线方法相比,显示出更高的准确性和更低的开销。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Dynamic Split Federated Learning for resource-constrained IoT systems
Efficient resource utilization in Internet of Things (IoT) systems is challenging due to device limitations. These limitations restrict on-device machine learning (ML) model training, leading to longer processing times and inefficient metadata analysis. Additionally, conventional centralized data collection poses privacy concerns, as raw data has to leave the device to the server for processing. Combining Federated Learning (FL) and Split Learning (SL) offers a promising solution by enabling effective machine learning on resource-constrained devices while preserving user privacy. However, the dynamic nature of IoT resources and device heterogeneity can complicate the application of these solutions, as some IoT devices cannot complete the training task on time. To address these concerns, we have developed a Dynamic Split Federated Learning (DSFL) architecture that dynamically adjusts to the real-time resource availability of individual clients. Combining real-time split-point selection with a Genetic Algorithm (GA) for client selection, tailored to heterogeneous, resource-constrained IoT devices. DSFL ensures optimal utilization of resources and efficient training across heterogeneous IoT devices and servers. Our architecture detects each IoT device’s training capabilities by identifying the number of layers it can train. Moreover, an effective Genetic Algorithm (GA) process strategically selects the clients required to complete the split federated learning round. Cooperatively, the clients and servers train their parts of the model, aggregate them, and then combine the results before moving to the next round. Our proposed architecture enables collaborative model training across devices while preserving data privacy by combining FL’s parallelism with SL’s dynamic modeling. We evaluated our architecture on sensory and image-based datasets, showing improved accuracy and reduced overhead compared to baseline methods.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Computer Communications
Computer Communications 工程技术-电信学
CiteScore
14.10
自引率
5.00%
发文量
397
审稿时长
66 days
期刊介绍: Computer and Communications networks are key infrastructures of the information society with high socio-economic value as they contribute to the correct operations of many critical services (from healthcare to finance and transportation). Internet is the core of today''s computer-communication infrastructures. This has transformed the Internet, from a robust network for data transfer between computers, to a global, content-rich, communication and information system where contents are increasingly generated by the users, and distributed according to human social relations. Next-generation network technologies, architectures and protocols are therefore required to overcome the limitations of the legacy Internet and add new capabilities and services. The future Internet should be ubiquitous, secure, resilient, and closer to human communication paradigms. Computer Communications is a peer-reviewed international journal that publishes high-quality scientific articles (both theory and practice) and survey papers covering all aspects of future computer communication networks (on all layers, except the physical layer), with a special attention to the evolution of the Internet architecture, protocols, services, and applications.
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信