A two-stage federated optimization algorithm for privacy computing in Internet of Things

被引:9
作者
Zhang, Jiangjiang [1 ]
Ning, Zhenhu [1 ]
Xue, Fei [2 ]
机构
[1] Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
[2] Beijing Wuzi Univ, Sch Informat, Beijing 101149, Peoples R China
来源
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE | 2023年 / 145卷
基金
中国国家自然科学基金;
关键词
Federated optimization algorithm; Robust; Multitasking learning; Privacy protection; Two-stage; CLIENT SELECTION; NETWORKS;
D O I
10.1016/j.future.2023.03.042
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
With the advent of the Internet of things (IoT) era, federated learning plays an important role in breaking through traditional data barriers and effectively realizing data privacy and security in the process of sharing. However, the demand of the practical problems makes the algorithm still have great challenges in effectively balancing various factors, such as privacy security, accuracy, computing efficiency and so on. To challenge this problem, a two-stage federated optimization algorithm based on robust and multitasking learning is designed. In optimization client local model stage, an adaptive weight assignment mechanism is adopted to guide robust learning based on multiple untrusted sources data, which aims to ensure the credibility and robustness of the client model and obtain a reliable client model. To address the information leakage problem during the server-client global model optimization stage, a privacy patch layer is added to the client local model in multitask learning and maintain its privacy parameters stored on the client model during the global model parameter aggregation process, which aims to meet the personalized requirements and performance requirements of protecting the model privacy. To effectively measure the performance of our algorithm, two extensive experiments are carried out to verify the robustness and accuracy of model under different datasets, respectively. In addition, simulation results show that our algorithm successfully suppresses the impact of corrupted or irrelevant sources on performance, and its performance is better than the other two robust distributed learning baseline methods in the client local model optimization stage. At the same time, our algorithm achieves better accuracy performance than other advanced personalized optimization algorithms in the server-client global model optimization stage. Finally, it achieves a good balance between robustness, computational efficiency and model privacy protection.(c) 2023 Elsevier B.V. All rights reserved.
引用
收藏
页码:354 / 366
页数:13
相关论文
共 50 条
[41]   Research on privacy protection system of RFID personal consumption data based on internet of things and cloud computing [J].
Du N. ;
Chen C. .
International Journal of Information and Computer Security, 2021, 15 (04) :328-342
[42]   An archive-based two-stage evolutionary algorithm for constrained multi-objective optimization problems [J].
Bao, Qian ;
Wang, Maocai ;
Dai, Guangming ;
Chen, Xiaoyu ;
Song, Zhiming ;
Li, Shuijia .
SWARM AND EVOLUTIONARY COMPUTATION, 2022, 75
[43]   A knowledge driven two-stage co-evolutionary algorithm for constrained multi-objective optimization [J].
Zhang, Wei ;
Liu, Jianchang ;
Li, Lin ;
Liu, Yuanchao ;
Wang, Honghai .
EXPERT SYSTEMS WITH APPLICATIONS, 2025, 274
[44]   DITGOssi: a two-stage invasive tumor growth optimization algorithm for the detection of SNP-SNP interactions [J].
Tan, Kaiwen ;
Dong, Shoubing ;
Zhou, Jing ;
Hu, Jinlong .
PROCEEDINGS 2018 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM), 2018, :1796-1801
[45]   Federated Learning-Empowered Disease Diagnosis Mechanism in the Internet of Medical Things: From the Privacy-Preservation Perspective [J].
Wang, Xiaoding ;
Hu, Jia ;
Lin, Hui ;
Liu, Wenxin ;
Moon, Hyeonjoon ;
Piran, Md. Jalil .
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2023, 19 (07) :7905-7913
[46]   Two-Stage Client Selection Scheme for Blockchain-Enabled Federated Learning in IoT [J].
Jin, Xiaojun ;
Ma, Chao ;
Luo, Song ;
Zeng, Pengyi ;
Wei, Yifei .
CMC-COMPUTERS MATERIALS & CONTINUA, 2024, 81 (02) :2317-2336
[47]   Adaptive Transmission Optimization in SDN-Based Industrial Internet of Things With Edge Computing [J].
Li, Xiaomin ;
Li, Di ;
Wan, Jiafu ;
Liu, Chengliang ;
Imran, Muhammad .
IEEE INTERNET OF THINGS JOURNAL, 2018, 5 (03) :1351-1360
[48]   Energy and Distribution-Aware Cooperative Clustering Algorithm in Internet of Things (IoT)-Based Federated Learning [J].
Lee, Jaewook ;
Ko, Haneul .
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2023, 72 (10) :13799-13804
[49]   Enhancing Portfolio Optimization: A Two-Stage Approach with Deep Learning and Portfolio Optimization [J].
Huang, Shiguo ;
Cao, Linyu ;
Sun, Ruili ;
Ma, Tiefeng ;
Liu, Shuangzhe .
MATHEMATICS, 2024, 12 (21)
[50]   A kind of two-stage RRT algorithm for robotic path planning [J].
Chen, X. (chenxiong@fudan.edu.cn), 1600, Inderscience Enterprises Ltd., 29, route de Pre-Bois, Case Postale 856, CH-1215 Geneva 15, CH-1215, Switzerland (06) :34-38