A hierarchical blockchain-enabled distributed federated learning system with model contribution based rewarding

作     者：Haibo Wang Hongwei Gao Teng Ma Chong Li Tao Jing Haibo Wang;Hongwei Gao;Teng Ma;Chong Li;Tao Jing

作者机构：The Research Institute of Broadband Wireless Mobile CommunicationBeijing Jiaotong UniversityBeijing100044China The Department of Electrical EngineeringColumbia UniversityNew York10027United States 

出 版 物：《Digital Communications and Networks》 (数字通信与网络(英文版))

年 卷 期：2025年第11卷第1期

页      面：35-42页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 0839[工学-网络空间安全] 08[工学] 081201[工学-计算机系统结构] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Blockchain Federated learning Consensus scheme Accuracy dependent throughput management 

摘      要：Distributed Federated Learning(DFL)technology enables participants to cooperatively train a shared model while preserving the privacy of their local datasets,making it a desirable solution for decentralized and privacy-preserving Web3 ***,DFL faces incentive and security challenges in the decentralized *** address these issues,this paper presents a Hierarchical Blockchain-enabled DFL(HBDFL)system,which provides a generic solution framework for the DFL-related *** proposed system consists of four major components,including a model contribution-based reward mechanism,a Proof of Elapsed Time and Accuracy(PoETA)consensus algorithm,a Distributed Reputation-based Verification Mechanism(DRTM)and an Accuracy-Dependent Throughput Management(ADTM)*** model contribution-based rewarding mechanism incentivizes network nodes to train models with their local datasets,while the PoETA consensus algorithm optimizes the tradeoff between the shared model accuracy and system *** DRTM improves the system efficiency in consensus,and the ADTM mechanism guarantees that the throughput performance remains within a predefined range while improving the shared model *** performance of the proposed HBDFL system is evaluated by numerical simulations,with the results showing that the system improves the accuracy of the shared model while maintaining high throughput and ensuring security.