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
  • [1] Semi-FedSER: Semi-supervised Learning for Speech Emotion Recognition On Federated Learning using Multiview Pseudo-Labeling
    Feng, Tiantian
    Narayanan, Shrikanth
    INTERSPEECH 2022, 2022, : 5050 - 5054
  • [2] A Semi-Supervised Learning Method for Spiking Neural Networks Based on Pseudo-Labeling
    Nguyen, Thao N. N.
    Veeravalli, Bharadwaj
    Fong, Xuanyao
    2023 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN, 2023,
  • [3] GENERALIZED PSEUDO-LABELING IN CONSISTENCY REGULARIZATION FOR SEMI-SUPERVISED LEARNING
    Karaliolios, Nikolaos
    Chabot, Florian
    Dupont, Camille
    Le Borgne, Herve
    Quoc-Cuong Pham
    Audigier, Romaric
    2023 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP, 2023, : 525 - 529
  • [4] Pseudo-Labeling Using Gaussian Process for Semi-supervised Deep Learning
    Li, Zhun
    Ko, ByungSoo
    Choi, Hojin
    2018 IEEE INTERNATIONAL CONFERENCE ON BIG DATA AND SMART COMPUTING (BIGCOMP), 2018, : 263 - 269
  • [5] FedIDE: Federated Semi-Supervised Learning With Instance Discrimination & LocalEMA
    Gao, Zhipeng
    Niu, Shaolong
    Zhao, Chen
    Yang, Yang
    ICC 2024 - IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS, 2024, : 3268 - 3273
  • [6] DYMatch: Semi-Supervised Learning with Dynamic Pseudo Labeling and Feature Consistency
    Mao, Zhongjie
    Pan, Feng
    Sun, Jun
    APPLIED SCIENCES-BASEL, 2024, 14 (01):
  • [7] Boosting semi-supervised learning under imbalanced regression via pseudo-labeling
    Zong, Nannan
    Su, Songzhi
    Zhou, Changle
    CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2024, 36 (19):
  • [8] Cformer: Semi-Supervised Text Clustering Based on Pseudo Labeling
    Hatefi, Arezoo
    Vu, Xuan-Son
    Bhuyan, Monowar
    Drewes, Frank
    PROCEEDINGS OF THE 30TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT, CIKM 2021, 2021, : 3078 - 3082
  • [9] Momentum Pseudo-Labeling for Semi-Supervised Speech Recognition
    Higuchi, Yosuke
    Moritz, Niko
    Le Roux, Jonathan
    Hori, Takaaki
    INTERSPEECH 2021, 2021, : 726 - 730
  • [10] Semi-supervised federated learning on evolving data streams
    Mawuli, Cobbinah B.
    Kumar, Jay
    Nanor, Ebenezer
    Fu, Shangxuan
    Pan, Liangxu
    Yang, Qinli
    Zhang, Wei
    Shao, Junming
    INFORMATION SCIENCES, 2023, 643