Joint Representation Learning

Joint Representation Learning is a computational approach that, as a member of the class of multi-omics integration methods, constructs a unified latent representation by simultaneously modeling shared and complementary patterns across multiple biological data modalities to enable downstream analyses.

850

Publications

62.1K

Citations

3K

Authors

801

Institutions

Publications per year

2017–2026

657

Variants

Jrl

Authors

3K

  1. DS
    Dinggang Shen

    University of North Carolina at Chapel Hill, United States

    17 publications · 2.4K citations

    15

    h-index

  2. XM
    Xiaoke Ma

    Xidian University, China

    7 publications · 221 citations

    7

    h-index

  3. BL
    Baiying Lei

    Shenzhen University, China

    7 publications · 465 citations

    7

    h-index

  4. JZ
    Jun Zhang

    Tencent (China), China

    6 publications · 615 citations

    6

    h-index

  5. JY
    Jian Yang

    Nanjing University of Science and Technology, China

    6 publications · 1.1K citations

    6

    h-index

1–5 of 3K

Venues

  1. arXiv (Cornell University)

    Repository · 86 publications · 4.5K citations

    33

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 29 publications · 1.8K citations

    22

    h-index

  3. IEEE Transactions on Image Processing

    27 publications · 2.5K citations

    22

    h-index

  4. IEEE Transactions on Pattern Analysis and Machine Intelligence

    TPAMI · 22 publications · 4.7K citations

    21

    h-index

  5. 16

    h-index

1–5