Concepedia

Self-training

Self-Training is a semi-supervised learning approach in which a model initially trained on labeled data iteratively generates pseudo-labels for unlabeled data and subsequently retrains itself by incorporating these high-confidence predictions as if they were true labels.

1.1K

Publications

72.6K

Citations

3.9K

Authors

1.2K

Institutions

Publications per year

2017–2026

626

Parents

Publications

1.1K

Deeper Insights Into Graph Convolutional Networks for Semi-Supervised Learning

Qimai Li, Zhichao Han, Xiao-Ming Wu · Proceedings of the AAAI Conference on Artificial Intelligence · 2018 · 2.6K citations · Full text

, , +16

GeneMarkS: a self-training method for prediction of gene starts in microbial genomes. Implications for finding sequence motifs in regulatory regions

J Besemer · Nucleic Acids Research · 2001 · 2.4K citations · Full text

, , +14

Self-Training With Noisy Student Improves ImageNet Classification

Qizhe Xie, Minh-Thang Luong, Eduard Hovy et al. · 2020 · 2.3K citations

, , +14

Self-taught learning

Rajat Raina, Alexis Battle, Honglak Lee et al. · 2007 · 1.5K citations

, , +13

An Empirical Study of Training Self-Supervised Vision Transformers

Xinlei Chen, Saining Xie, Kaiming He · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · 2021 · 1.5K citations

, , +12

1–5 of 1.1K

Authors

3.9K

  1. QV
    Quoc V. Le

    Google (United States), United States

    7 publications · 3.3K citations

    7

    h-index

  2. CZ
    Chao Zhang

    University of Illinois Urbana-Champaign, United States

    6 publications · 523 citations

    6

    h-index

  3. JH
    Jiawei Han

    University of Illinois Urbana-Champaign, United States

    5 publications · 466 citations

    5

    h-index

  4. MA
    Michael Auli

    Meta (Israel), Israel

    5 publications · 305 citations

    5

    h-index

  5. PL
    Percy Liang

    Stanford University, United States

    5 publications · 324 citations

    5

    h-index

1–5 of 3.9K

Institutions

1.2K

  1. Google (United States)

    Mountain View, United States

    17 h-index

    94 publications

    21.6K citations

  2. Tsinghua University

    Beijing, China

    16 h-index

    40 publications

    2K citations

  3. Chinese Academy of Sciences

    Beijing, China

    16 h-index

    40 publications

    1.9K citations

  4. Stanford University

    Stanford, United States

    15 h-index

    46 publications

    11.1K citations

  5. University of Chinese Academy of Sciences

    Beijing, China

    14 h-index

    37 publications

    1.8K citations

  6. University of Washington

    Seattle, United States

    14 h-index

    38 publications

    2.8K citations

  7. Georgia Institute of Technology

    Atlanta, United States

    14 h-index

    35 publications

    7.2K citations

  8. Peking University

    Beijing, China

    13 h-index

    45 publications

    2.5K citations

1–8 of 1.2K

Venues

  1. arXiv (Cornell University)

    Repository · 95 publications · 5.6K citations

    37

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 28 publications · 4.6K citations

    22

    h-index

  3. 17

    h-index

  4. 13

    h-index

  5. IEEE Access

    13 publications · 383 citations

    12

    h-index

1–5