Disentangled Representation Learning

Disentangled Representation Learning is a representation learning framework that seeks to identify and separate the underlying explanatory factors of data variation into statistically independent components within the learned latent space.

634

Publications

41.8K

Citations

2.1K

Authors

486

Institutions

Publications per year

2017–2026

619

Authors

2.1K

  1. BS
    Bernhard Schölkopf

    Max Planck Institute for Intelligent Systems, Germany

    20 publications · 1.5K citations

    17

    h-index

  2. FL
    Francesco Locatello

    Max Planck Institute for Intelligent Systems, Germany

    17 publications · 1.5K citations

    15

    h-index

  3. SB
    Stefan Bauer

    Max Planck Institute for Intelligent Systems, Germany

    15 publications · 1.3K citations

    14

    h-index

  4. AL
    Alexander Lerchner

    Google (United States), United States

    14 publications · 4.7K citations

    14

    h-index

  5. IH
    Irina Higgins

    Google (United States), United States

    13 publications · 4.4K citations

    13

    h-index

1–5 of 2.1K

Venues

  1. arXiv (Cornell University)

    Repository · 193 publications · 11.4K citations

    51

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 26 publications · 1.7K citations

    20

    h-index

  3. 13

    h-index

  4. IEEE Transactions on Pattern Analysis and Machine Intelligence

    TPAMI · 13 publications · 1.4K citations

    13

    h-index

  5. IEEE Transactions on Multimedia

    12 publications · 713 citations

    12

    h-index

1–5