Evolutionary Multi-model Federated Learning on Malicious and Heterogeneous Data

被引:2
|
作者
Shang, Chikai [1 ]
Gu, Fangqing [1 ]
Jiang, Jiaqi [1 ]
机构
[1] Guangdong Univ Technol, Sch Math & Stat, Guangzhou, Guangdong, Peoples R China
来源
2023 23RD IEEE INTERNATIONAL CONFERENCE ON DATA MINING WORKSHOPS, ICDMW 2023 | 2023年
关键词
Federated learning; particle swarm optimization; heterogeneous data; malicious data;
D O I
10.1109/ICDMW60847.2023.00055
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The federated learning system is vulnerable to data poisoning attacks from malicious clients, who often present heterogeneous data. Poisoning such heterogeneous data can lead to significant diversity in the local datasets. Traditional singlemodel federated learning struggles to effectively handle this diverse knowledge. To address this challenge, we propose an evolutionary multi-model federated learning framework called EMFL, which trains multiple models with diversity to learn from the diverse data effectively. Specifically, we introduce a gradientbased particle swarm optimization approach, which incorporates gradient information from the models and utilizes a multielite strategy to achieve quick convergence and promote model diversity. Furthermore, we propose a client-matching strategy based on cosine similarity of multi-model updates, allowing for analyzing the similarity of distribution patterns in diverse data and matching clients with concentrated distributions, thus helping to prevent excessive models from converging to malicious data and causing extreme model diversity. The proposed EMFL employs multiple lightweight models instead of a large architecture one to overcome training challenges for clients with limited computing power. Experimental results on nine datasets demonstrate consistent outperformance of our proposed algorithm compared to its counterparts.
引用
收藏
页码:386 / 395
页数:10
相关论文
共 50 条
  • [1] Cooperative Multi-Model Training for Personalized Federated Learning Over Heterogeneous Devices
    Xu, Jian
    Wan, Shuo
    Li, Yinchuan
    Luo, Sichun
    Chen, Zhilin
    Shao, Yunfeng
    Chen, Zhitang
    Huang, Shao-Lun
    Song, Linqi
    IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2025, 19 (01) : 195 - 207
  • [2] An Efficient Multi-Model Training Algorithm for Federated Learning
    Li, Cong
    Li, Chunxi
    Zhao, Yongxiang
    Zhang, Baoxian
    Li, Cheng
    2021 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM), 2021,
  • [3] Robust Federated Learning for Heterogeneous Model and Data
    Madni, Hussain Ahmad
    Umer, Rao Muhammad
    Foresti, Gian Luca
    INTERNATIONAL JOURNAL OF NEURAL SYSTEMS, 2024, 34 (04)
  • [4] Robust Multi-model Personalized Federated Learning via Model Distillation
    Muhammad, Adil
    Lin, Kai
    Gao, Jian
    Chen, Bincai
    ALGORITHMS AND ARCHITECTURES FOR PARALLEL PROCESSING, ICA3PP 2021, PT III, 2022, 13157 : 432 - 446
  • [5] MULTI-MODEL FEDERATED LEARNING OPTIMIZATION BASED ON MULTI-AGENT REINFORCEMENT LEARNING
    Atapour, S. Kaveh
    Seyedmohammadi, S. Jamal
    Sheikholeslami, S. Mohammad
    Abouei, Jamshid
    Mohammadi, Arash
    Plataniotis, Konstantinos N.
    2023 IEEE 9TH INTERNATIONAL WORKSHOP ON COMPUTATIONAL ADVANCES IN MULTI-SENSOR ADAPTIVE PROCESSING, CAMSAP, 2023, : 151 - 155
  • [6] Joint Participant Selection and Learning Scheduling for Multi-Model Federated Edge Learning
    Wei, Xinliang
    Liu, Jiyao
    Wang, Yu
    2022 IEEE 19TH INTERNATIONAL CONFERENCE ON MOBILE AD HOC AND SMART SYSTEMS (MASS 2022), 2022, : 537 - 545
  • [7] Evolutionary Model Owner Selection for Federated Learning with Heterogeneous Privacy Budgets
    Lim, Wei Yang Bryan
    Ng, Jer Shyuan
    Nie, Jiangtian
    Hu, Qin
    Xiong, Zehui
    Niyato, Dusit
    Miao, Chunyan
    IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC 2022), 2022, : 980 - 985
  • [8] Multi-model partitioning the multi-model evolutionary framework for intelligent control
    Lainiotis, DG
    PROCEEDINGS OF THE 2000 IEEE INTERNATIONAL SYMPOSIUM ON INTELLIGENT CONTROL, 2000, : P15 - P20
  • [9] Uplink Over-the-Air Aggregation for Multi-Model Wireless Federated Learning
    Zhang, Chong
    Dong, Min
    Liang, Ben
    Afanat, Ali
    Ahmed, Yahia
    2024 IEEE 25TH INTERNATIONAL WORKSHOP ON SIGNAL PROCESSING ADVANCES IN WIRELESS COMMUNICATIONS, SPAWC 2024, 2024, : 36 - 40
  • [10] Understanding and Improving Model Averaging in Federated Learning on Heterogeneous Data
    Zhou, Tailin
    Lin, Zehong
    Zhang, Jun
    Tsang, Danny H. K.
    IEEE TRANSACTIONS ON MOBILE COMPUTING, 2024, 23 (12) : 12131 - 12145