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
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] Semi-HFL: semi-supervised federated learning for heterogeneous devices
    Zhengyi Zhong
    Ji Wang
    Weidong Bao
    Jingxuan Zhou
    Xiaomin Zhu
    Xiongtao Zhang
    Complex & Intelligent Systems, 2023, 9 : 1995 - 2017
  • [32] Semi-HFL: semi-supervised federated learning for heterogeneous devices
    Zhong, Zhengyi
    Wang, Ji
    Bao, Weidong
    Zhou, Jingxuan
    Zhu, Xiaomin
    Zhang, Xiongtao
    COMPLEX & INTELLIGENT SYSTEMS, 2023, 9 (02) : 1995 - 2017
  • [33] Rethinking Pseudo-Labeling for Semi-Supervised Facial Expression Recognition With Contrastive Self-Supervised Learning
    Fang, Bei
    Li, Xian
    Han, Guangxin
    He, Juhou
    IEEE ACCESS, 2023, 11 : 45547 - 45558
  • [34] Tracking with Context as a Semi-supervised Learning and Labeling Problem
    Cerman, Lukas
    Hlavac, Vaclav
    2012 21ST INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR 2012), 2012, : 2124 - 2127
  • [35] Boosting semi-supervised learning with Contrastive Complementary Labeling
    Deng, Qinyi
    Guo, Yong
    Yang, Zhibang
    Pan, Haolin
    Chen, Jian
    NEURAL NETWORKS, 2024, 170 : 417 - 426
  • [36] Learning to select pseudo labels: a semi-supervised method for named entity recognition
    Zhen-zhen Li
    Da-wei Feng
    Dong-sheng Li
    Xi-cheng Lu
    Frontiers of Information Technology & Electronic Engineering, 2020, 21 : 903 - 916
  • [37] Self-Supervised Wasserstein Pseudo-Labeling for Semi-Supervised Image Classification
    Taherkhani, Fariborz
    Dabouei, Ali
    Soleymani, Sobhan
    Dawson, Jeremy
    Nasrabadi, Nasser M.
    2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 12262 - 12272
  • [38] Learning to select pseudo labels: a semi-supervised method for named entity recognition
    Li, Zhen-zhen
    Feng, Da-wei
    Li, Dong-sheng
    Lu, Xi-cheng
    FRONTIERS OF INFORMATION TECHNOLOGY & ELECTRONIC ENGINEERING, 2020, 21 (06) : 903 - 916
  • [39] Navigating Data Heterogeneity in Federated Learning: A Semi-Supervised Federated Object Detection
    Kim, Taehyeon
    Lin, Eric
    Lee, Junu
    Lau, Christian
    Mugunthan, Vaikkunth
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [40] PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection
    Li, Gang
    Li, Xiang
    Wang, Yujie
    Wu, Yichao
    Liang, Ding
    Zhang, Shanshan
    COMPUTER VISION, ECCV 2022, PT IX, 2022, 13669 : 457 - 472