FedGen: Personalized federated learning with data generation for enhanced model customization and class imbalance

被引:0
|
作者
Zhao, Peng [1 ,2 ]
Guo, Shaocong [1 ,2 ]
Li, Yanan [4 ]
Yang, Shusen [2 ,3 ]
Ren, Xuebin
机构
[1] Xi An Jiao Tong Univ, Sch Comp Sci & Technol, Xian 710049, Peoples R China
[2] Xi An Jiao Tong Univ, Natl Engn Lab Big Data Analyt, Xian 710049, Peoples R China
[3] Xi An Jiao Tong Univ, Minist Educ, Key Lab Intelligent Networks & Network Secur, Xian 710049, Peoples R China
[4] Henan Polytech Univ, Sch Software, Jiaozuo 454003, Peoples R China
关键词
Personalized federated learning; Generative adversarial networks; Class imbalance problem; Structured data; Data generation; Model customization; PRIVACY;
D O I
10.1016/j.future.2024.107595
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Federated learning has emerged as a prominent solution for the collaborative training of machine learning models without exchanging local data. However, existing approaches often impose rigid constraints on model heterogeneity, limiting the ability of clients to customize unique models and increasing the vulnerability of models to potential attacks. This paper presents FedGen, a novel personalized federated learning framework based on generative adversarial networks (GANs). FedGen shifts the focus from training task-specific models to generating data, especially for minority classes with imbalanced data. With FedGen, clients can gain knowledge from others by training generators, while maintaining a heterogeneous local model and avoiding sharing model information with other participants. Moreover, to address challenges arising from imbalanced data, we propose AT-GAN, a novel generative model incorporating pseudo augmentation and differentiable augmentation modules to foster healthy competition between the generator and discriminator. To evaluate the effectiveness of our approach, we conduct extensive experiments on real-world tabular datasets. The experimental results demonstrate that FedGen significantly enhances the performance of local models, achieving improvements of up to 11.92% in F1 score and up to 9.14% in MCC score compared to existing methods.
引用
收藏
页数:9
相关论文
共 50 条
  • [1] FedGen: Generalizable Federated Learning for Sequential Data
    Venkateswaran, Praveen
    Isahagian, Vatche
    Muthusamy, Vinod
    Venkatasubramanian, Nalini
    2023 IEEE 16TH INTERNATIONAL CONFERENCE ON CLOUD COMPUTING, CLOUD, 2023, : 308 - 318
  • [2] FEDERATED LEARNING WITH CLASS IMBALANCE REDUCTION
    Yang, Miao
    Wang, Ximin
    Zhu, Hongbin
    Wang, Haifeng
    Qian, Hua
    29TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2021), 2021, : 2174 - 2178
  • [3] Addressing Class Imbalance in Federated Learning
    Wang, Lixu
    Xu, Shichao
    Wang, Xiao
    Zhu, Qi
    THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 10165 - 10173
  • [4] An Experimental Study of Class Imbalance in Federated Learning
    Xiao, Chenguang
    Wang, Shuo
    2021 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (IEEE SSCI 2021), 2021,
  • [5] MpFedcon: Model-Contrastive Personalized Federated Learning with the Class Center
    LI Xingchen
    FANG Zhijun
    SHI Zhicai
    WuhanUniversityJournalofNaturalSciences, 2022, 27 (06) : 508 - 520
  • [6] Class-Balanced Federated Learning Based on Data Generation
    Li Z.-P.
    Guo Y.
    Chen Y.-F.
    Wang Y.-W.
    Zeng W.
    Tan M.-K.
    Jisuanji Xuebao/Chinese Journal of Computers, 2023, 46 (03): : 609 - 625
  • [7] FedISM: Enhancing Data Imbalance via Shared Model in Federated Learning
    Chung, Wu-Chun
    Lin, Yan-Hui
    Fang, Sih-Han
    MATHEMATICS, 2023, 11 (10)
  • [8] Harmonizing Global and Local Class Imbalance for Federated Learning
    Zhu, Jialiang
    Zheng, Hao
    Xu, Wenchao
    Wang, Haozhao
    He, Zhiming
    Liu, Yuxuan
    Wang, Shuang
    Sun, Qi
    IEEE TRANSACTIONS ON MOBILE COMPUTING, 2025, 24 (02) : 1120 - 1131
  • [9] Performance Enhancement in Federated Learning by Reducing Class Imbalance of Non-IID Data
    Seol, Mihye
    Kim, Taejoon
    SENSORS, 2023, 23 (03)
  • [10] Sparse personalized federated class-incremental learning
    Liu, Youchao
    Huang, Dingjiang
    INFORMATION SCIENCES, 2025, 706