Non-negative Matrix Factorization

Non-Negative Matrix Factorization is a matrix decomposition method in unsupervised learning that factorizes a non-negative data matrix into the product of two lower-dimensional, non-negative matrices, capturing latent features through additive, parts-based representations.

3.2K

Publications

245K

Citations

8.1K

Authors

2.1K

Institutions

Publications per year

2017–2026

1.4K

Authors

8.1K

  1. XL
    Xin Luo

    Chongqing Institute of Green and Intelligent Technology, China

    39 publications · 4.2K citations

    29

    h-index

  2. AC
    Andrzej Cichocki

    RIKEN Center for Brain Science, Japan

    36 publications · 3.3K citations

    28

    h-index

  3. NG
    Nicolas Gillis

    University of Mons, Belgium

    26 publications · 1.6K citations

    22

    h-index

  4. HP
    Haesun Park

    Georgia Institute of Technology, United States

    26 publications · 4.8K citations

    21

    h-index

  5. CF
    Cédric Févotte

    Centre National de la Recherche Scientifique, France

    25 publications · 4.1K citations

    21

    h-index

1–5 of 8.1K

Venues

  1. Neurocomputing

    77 publications · 3.2K citations

    35

    h-index

  2. 33

    h-index

  3. Pattern Recognition

    45 publications · 3.6K citations

    32

    h-index

  4. IEEE Transactions on Image Processing

    36 publications · 3.7K citations

    30

    h-index

  5. arXiv (Cornell University)

    Repository · 91 publications · 5.2K citations

    30

    h-index

1–5