Semi-supervised Representation Learning

Semi-Supervised Representation Learning is a machine learning paradigm that belongs to the broader category of representation learning methods, distinguished by its use of both labeled and unlabeled data to learn effective feature representations through the integration of supervised and unsupervised learning signals.

1.9K

Publications

155.7K

Citations

5.7K

Authors

1.3K

Institutions

Publications per year

2017–2026

1.2K

Authors

5.7K

  1. FN
    Feiping Nie

    Northwestern Polytechnical University, China

    28 publications · 1.9K citations

    23

    h-index

  2. ZZ
    Zhao Zhang

    Hefei University of Technology, China

    15 publications · 748 citations

    14

    h-index

  3. CZ
    Changshui Zhang

    Tsinghua University, China

    14 publications · 1.6K citations

    13

    h-index

  4. LJ
    Licheng Jiao

    Xidian University, China

    12 publications · 361 citations

    12

    h-index

  5. YB
    Yoshua Bengio

    Université de Montréal, Canada

    12 publications · 4.1K citations

    12

    h-index

1–5 of 5.7K

Venues

  1. arXiv (Cornell University)

    Repository · 190 publications · 36.3K citations

    57

    h-index

  2. Pattern Recognition

    64 publications · 3.4K citations

    35

    h-index

  3. Neurocomputing

    76 publications · 2.8K citations

    31

    h-index

  4. Information Sciences

    40 publications · 1.7K citations

    28

    h-index

  5. IEEE Transactions on Knowledge and Data Engineering

    TKDE · 31 publications · 3.4K citations

    26

    h-index

1–5