Transductive Graph Learning

Transductive Graph Learning is a graph-based learning paradigm that, as a member of the broader class of semi-supervised learning methods, specifically performs inference by leveraging both labeled and unlabeled nodes within a fixed graph to predict labels for the originally unlabeled nodes, distinguishing itself through the assumption that the entire node set is known during training and that no generalization beyond this set is required.

113

Publications

32.4K

Citations

363

Authors

169

Institutions

Publications per year

2017–2026

66

Authors

363

  1. YB
    Yoshua Bengio

    Université de Montréal, Canada

    5 publications · 9.9K citations

    5

    h-index

  2. FN
    Feiping Nie

    Northwestern Polytechnical University, China

    5 publications · 273 citations

    5

    h-index

  3. PV
    Petar Veličković

    Google (United States), United States

    5 publications · 1.5K citations

    5

    h-index

  4. FW
    Fei Wu

    Zhejiang University, China

    4 publications · 414 citations

    4

    h-index

  5. PL
    Píetro Lió

    University of Cambridge, United Kingdom

    4 publications · 1.5K citations

    4

    h-index

1–5 of 363

Venues

  1. arXiv (Cornell University)

    Repository · 25 publications · 15.1K citations

    17

    h-index

  2. IEEE Transactions on Image Processing

    5 publications · 807 citations

    5

    h-index

  3. 4

    h-index

  4. Pattern Recognition

    3 publications · 83 citations

    3

    h-index

  5. IEEE Transactions on Multimedia

    3 publications · 221 citations

    3

    h-index

1–5