Personalized User Models in a Real-world Edge Computing Environment: A Peer-to-peer Federated Learning Framework

作     者：Song, Xiangchi Wang, Zhaoyan Baek, Kyeongdeok Ko, In-Young 

作者机构：Korea Adv Inst Sci & Technol Daejeon South Korea 

出 版 物：《JOURNAL OF WEB ENGINEERING》 (J. Web Eng.)

年 卷 期：2024年第23卷第8期

页      面：1057-1084页

核心收录：

学科分类：08[工学] 0835[工学-软件工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：MSIT (Ministry of Science and ICT) , Korea, under the ITRC (Information Technology Research Center) support program [IITP-2024-2020-0-01795] IITP - Korea government (MSIT) [RS-2024-00406245] 

主　　题：personalized federated learning hierarchical edge computing edge-cloud environment 

摘      要：As the number of IoT devices and the volume of data increase, distributed computing systems have become the primary deployment solution for largescale Internet of Things (IoT) environments. Federated learning (FL) is a collaborative machine learning framework that allows for model training using data from all participants while protecting their privacy. However, traditional FL suffers from low computational and communication efficiency in large-scale hierarchical cloud-edge collaborative IoT systems. Additionally, due to heterogeneity issues, not all IoT devices necessarily benefit from the global model of traditional FL, but instead require the maintenance of personalized levels in the global training process. Therefore we extend FL into a horizontal peer-to-peer (P2P) structure and introduce our P2PFL framework: efficient peer-to-peer federated learning for users (EPFLU). EPFLU transitions the paradigms from vertical FL to a horizontal P2P structure from the user perspective and incorporates personalized enhancement techniques using private information. Through horizontal consensus Xiangchi Song information aggregation and private information supplementation, EPFLU solves the weakness of traditional FL that dilutes the characteristics of individual client data and leads to model deviation. This structural transformation also significantly alleviates the original communication issues. Additionally, EPFLU has a customized simulation evaluation framework, and uses the EUA dataset containing real-world edge server distribution, making it more suitable for real-world large-scale IoT. Within this framework, we design two extreme data distribution scenarios and conduct detailed experiments of EPFLU and selected baselines on the MNIST and CIFAR-10 datasets. The results demonstrate that the robust and adaptive EPFLU framework can consistently converge to optimal performance even under challenging data distribution scenarios. Compared with the traditional FL and selected P2