{"title":"阅读:具有细粒度层聚合和分散聚类的个性化联邦学习框架","authors":"Haoyu Fu;Fengsen Tian;Guoqiang Deng;Lingyu Liang;Xinglin Zhang","doi":"10.1109/TMC.2025.3552982","DOIUrl":null,"url":null,"abstract":"The heterogeneity of local data and client performance, along with real-world system risks, is driving the evolution of federated learning (FL) towards personalized, model-heterogeneous, and decentralized approaches. However, due to the differing structures of heterogeneous models, it is hard to use them to identify clients with similar data distributions and further enhance the personalization of local models. Therefore, how to deal with data heterogeneity to obtain superior personalized local models for clients, while simultaneously addressing model heterogeneity and system risks is a challenging problem. In this paper, we propose a novel personalized FL framework with fine-g<u>R</u>ained lay<u>E</u>r aggreg<u>A</u>tion and <u>D</u>ecentralized clu<u>S</u>tering (<inline-formula><tex-math>${\\sf Reads}$</tex-math></inline-formula>), which integrates four key components: (1) deep mutual learning with privacy guarantee for model training and privacy preservation, (2) fine-grained layer similarity computation among heterogeneous model layers, (3) fully decentralized clustering for soft clustering of clients based on layer similarities, and (4) personalized layer aggregation for capturing common knowledge from other clients. Through <inline-formula><tex-math>${\\sf Reads}$</tex-math></inline-formula>, clients obtain personalized models that accommodate model heterogeneity, while the system ensures robustness against a single point of failure. Extensive experiments demonstrate the efficacy of <inline-formula><tex-math>${\\sf Reads}$</tex-math></inline-formula> in achieving these goals.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 8","pages":"7709-7725"},"PeriodicalIF":9.2000,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Reads: A Personalized Federated Learning Framework With Fine-Grained Layer Aggregation and Decentralized Clustering\",\"authors\":\"Haoyu Fu;Fengsen Tian;Guoqiang Deng;Lingyu Liang;Xinglin Zhang\",\"doi\":\"10.1109/TMC.2025.3552982\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The heterogeneity of local data and client performance, along with real-world system risks, is driving the evolution of federated learning (FL) towards personalized, model-heterogeneous, and decentralized approaches. However, due to the differing structures of heterogeneous models, it is hard to use them to identify clients with similar data distributions and further enhance the personalization of local models. Therefore, how to deal with data heterogeneity to obtain superior personalized local models for clients, while simultaneously addressing model heterogeneity and system risks is a challenging problem. In this paper, we propose a novel personalized FL framework with fine-g<u>R</u>ained lay<u>E</u>r aggreg<u>A</u>tion and <u>D</u>ecentralized clu<u>S</u>tering (<inline-formula><tex-math>${\\\\sf Reads}$</tex-math></inline-formula>), which integrates four key components: (1) deep mutual learning with privacy guarantee for model training and privacy preservation, (2) fine-grained layer similarity computation among heterogeneous model layers, (3) fully decentralized clustering for soft clustering of clients based on layer similarities, and (4) personalized layer aggregation for capturing common knowledge from other clients. Through <inline-formula><tex-math>${\\\\sf Reads}$</tex-math></inline-formula>, clients obtain personalized models that accommodate model heterogeneity, while the system ensures robustness against a single point of failure. Extensive experiments demonstrate the efficacy of <inline-formula><tex-math>${\\\\sf Reads}$</tex-math></inline-formula> in achieving these goals.\",\"PeriodicalId\":50389,\"journal\":{\"name\":\"IEEE Transactions on Mobile Computing\",\"volume\":\"24 8\",\"pages\":\"7709-7725\"},\"PeriodicalIF\":9.2000,\"publicationDate\":\"2025-03-19\",\"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/10933559/\",\"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}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Mobile Computing","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10933559/","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}
Reads: A Personalized Federated Learning Framework With Fine-Grained Layer Aggregation and Decentralized Clustering
The heterogeneity of local data and client performance, along with real-world system risks, is driving the evolution of federated learning (FL) towards personalized, model-heterogeneous, and decentralized approaches. However, due to the differing structures of heterogeneous models, it is hard to use them to identify clients with similar data distributions and further enhance the personalization of local models. Therefore, how to deal with data heterogeneity to obtain superior personalized local models for clients, while simultaneously addressing model heterogeneity and system risks is a challenging problem. In this paper, we propose a novel personalized FL framework with fine-gRained layEr aggregAtion and Decentralized cluStering (${\sf Reads}$), which integrates four key components: (1) deep mutual learning with privacy guarantee for model training and privacy preservation, (2) fine-grained layer similarity computation among heterogeneous model layers, (3) fully decentralized clustering for soft clustering of clients based on layer similarities, and (4) personalized layer aggregation for capturing common knowledge from other clients. Through ${\sf Reads}$, clients obtain personalized models that accommodate model heterogeneity, while the system ensures robustness against a single point of failure. Extensive experiments demonstrate the efficacy of ${\sf Reads}$ in achieving these goals.
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.