计算机工程与科学2024，Vol.46Issue(7)：1237-1244,8.DOI:10.3969/j.issn.1007-130X.2024.07.012
基于异步分层联邦学习的数据异质性处理方法研究
A data heterogeneity processing method based on asynchronous hierarchical federated learning
摘要
Abstract
In the era of ubiquitous Internet of Things devices,a vast amount of data with varying dis-tributions and volumes is continuously generated,leading to pervasive data heterogeneity.Addressing the challenges of federated learning for intelligent devices in the IoT landscape,traditional synchronous federated learning mechanisms fall short in effectively tackling the NON-IID data distribution problem.Moreover,they are plagued by issues such as single-point failures and the complexity of maintaining a global clock.However,asynchronous mechanisms may introduce additional communication overhead and obsolescence due to NON-IID data distribution.To offer a more flexible solution to these chal-lenges,an asynchronous hierarchical federated learning method is proposed.Initially,the BIRCH algo-rithm is employed to analyze the data distribution across various IoT nodes,leading to the formation of clusters.Subsequently,data within these clusters is dissected and validated to identify nodes with high data quality.Nodes from high-quality clusters are then disaggregated and reorganized into lower-quality clusters,forming new,optimized clusters.Finally,a two-stage model training is conducted,involving both intra-cluster and global aggregation.Additionally,our proposed approach is evaluated using the MNIST dataset.The results show that,compared to the baseline set by the classical FedAVG method,the proposed approach achieves faster convergence on NON-IID datasets and improves model accuracy by more than 15%.关键词
物联网/联邦学习/异步联邦学习/分层联邦学习/数据异质性/数据分布Key words
Internet of Things(IoT)/federated learning/asynchronous federated learning/hierarchi-cal federated learning/non-independent and identically distributed data/data distribution分类
信息技术与安全科学引用本文复制引用
郭昌昊,唐湘云,翁彧..基于异步分层联邦学习的数据异质性处理方法研究[J].计算机工程与科学,2024,46(7):1237-1244,8.基金项目
国家自然科学基金青年基金(62302539) （62302539）
中央民族大学国家安全研究院边疆少数民族地区国家安全研究项目(2023GJAQ08) （2023GJAQ08）
