FedTriNet: A Pseudo Labeling Method with Three Players for Federated Semi-supervised Learning

被引:20
|
作者
Che, Liwei [1 ]
Long, Zewei [2 ]
Wang, Jiaqi [1 ]
Wang, Yaqing [3 ]
Xiao, Houping [4 ]
Ma, Fenglong [1 ]
机构
[1] Penn State Univ, Coll IST, State Coll, PA 16801 USA
[2] Univ Illinois, Dept Comp Sci, Champaign, IL USA
[3] Purdue Univ, Sch Elect & Comp Engn, W Lafayette, IN USA
[4] Georgia State Univ, Inst Insight, Atlanta, GA USA
来源
2021 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA) | 2021年
关键词
federated learning; semi-supervised learning; pseudo labeling;
D O I
10.1109/BigData52589.2021.9671374
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Federated Learning has shown great potentials for the distributed data utilization and privacy protection. Most existing federated learning approaches focus on the supervised setting, which means all the data stored in each client has labels. However, in real-world applications, the client data are impossible to be fully labeled. Thus, how to exploit the unlabeled data should be a new challenge for federated learning. Although a few studies are attempting to overcome this challenge, they may suffer from information leakage or misleading information usage problems. To tackle these issues, in this paper, we propose a novel federated semi-supervised learning method named FedTriNet, which consists of two learning phases. In the first phase, we pre-train FedTriNet using labeled data with FedAvg. In the second phase, we aim to make most of the unlabeled data to help model learning. In particular, we propose to use three networks and a dynamic quality control mechanism to generate high-quality pseudo labels for unlabeled data, which are added to the training set. Finally, FedTriNet uses the new training set to retrain the model. Experimental results on three publicly available datasets show that the proposed FedTriNet outperforms state-of-the-art baselines under both IID and Non-IID settings.
引用
收藏
页码:715 / 724
页数:10
相关论文
共 50 条
  • [31] Cross-Loss Pseudo Labeling for Semi-Supervised Segmentation
    Lee, Seungyeol
    Kim, Taeho
    Heo, Jae-Pil
    IEEE ACCESS, 2023, 11 : 96761 - 96772
  • [32] Growth threshold for pseudo labeling and pseudo label dropout for semi-supervised medical image classification
    Zhou, Shaofeng
    Tian, Shengwei
    Yu, Long
    Wu, Weidong
    Zhang, Dezhi
    Peng, Zhen
    Zhou, Zhicheng
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2024, 130
  • [33] Federated Cycling (FedCy): Semi-Supervised Federated Learning of Surgical Phases
    Kassem, Hasan
    Alapatt, Deepak
    Mascagni, Pietro
    Karargyris, Alexandros
    Padoy, Nicolas
    IEEE TRANSACTIONS ON MEDICAL IMAGING, 2023, 42 (07) : 1920 - 1931
  • [34] Federated Learning in Healthcare with Unsupervised and Semi-Supervised Methods
    Panos-Basterra, Juan
    Dolores Ruiz, M.
    Martin-Bautista, Maria J.
    FLEXIBLE QUERY ANSWERING SYSTEMS, FQAS 2023, 2023, 14113 : 182 - 193
  • [35] Pseudo Labeling Methods for Semi-Supervised Semantic Segmentation: A Review and Future Perspectives
    Ran, Lingyan
    Li, Yali
    Liang, Guoqiang
    Zhang, Yanning
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2025, 35 (04) : 3054 - 3080
  • [36] AdaptMatch: Adaptive Consistency Regularization for Semi-supervised Learning with Top-k Pseudo-labeling and Contrastive Learning
    Yang, Nan
    Huang, Fan
    Yuan, Dong
    ADVANCES IN ARTIFICIAL INTELLIGENCE, AI 2023, PT I, 2024, 14471 : 227 - 238
  • [37] Asynchronous Semi-Supervised Federated Learning with Provable Convergence in Edge Computing
    Yang, Nan
    Yuan, Dong
    Zhang, Yuning
    Deng, Yongkun
    Bao, Wei
    IEEE NETWORK, 2022, 36 (05): : 136 - 143
  • [38] Federated Semi-Supervised Learning with Local and Global Updating Frequency Optimization
    Hang, Xin
    Xu, Yang
    Xu, Hongli
    Liao, Yunming
    Wang, Lun
    2024 IEEE 24TH INTERNATIONAL SYMPOSIUM ON CLUSTER, CLOUD AND INTERNET COMPUTING, CCGRID 2024, 2024, : 255 - 265
  • [39] IMPROVED NOISY ITERATIVE PSEUDO-LABELING FOR SEMI-SUPERVISED SPEECH RECOGNITION
    Li, Tian
    Meng, Qingliang
    Sun, Yujian
    2022 IEEE SPOKEN LANGUAGE TECHNOLOGY WORKSHOP, SLT, 2022, : 167 - 173
  • [40] ACMFed: Fair Semi-Supervised Federated Learning With Additional Compromise Model
    Kim, Dohyoung
    Lee, Kangyoon
    Lee, Youngho
    Woo, Hyekyung
    IEEE ACCESS, 2025, 13 : 47734 - 47747