Selective Pruning

Selective Pruning is a model compression technique that systematically removes less informative neural network parameters based on sensitivity analysis to preserve critical model functionality while reducing computational complexity.

65

Publications

3.3K

Citations

213

Authors

107

Institutions

Publications per year

2017–2026

34

Authors

213

  1. FQ
    Fanchao Qi

    Tsinghua University, China

    2 publications · 40 citations

    2

    h-index

  2. ZL
    Zhiyuan Liu

    Tsinghua University, China

    2 publications · 40 citations

    2

    h-index

  3. QH
    Qiangui Huang

    University of Southern California, United States

    2 publications · 194 citations

    2

    h-index

  4. KZ
    Kevin Zhou

    Siemens (United States), United States

    2 publications · 194 citations

    2

    h-index

  5. UN
    Ulrich Neumann

    University of Southern California, United States

    2 publications · 194 citations

    2

    h-index

1–5 of 213

Venues

  1. arXiv (Cornell University)

    Repository · 11 publications · 703 citations

    11

    h-index

  2. Neurocomputing

    3 publications · 121 citations

    3

    h-index

  3. PLoS Computational Biology

    1 publications · 476 citations

    1

    h-index

  4. Journal of Imaging

    1 publications · 27 citations

    1

    h-index

  5. IEEE Transactions on Signal Processing

    1 publications · 17 citations

    1

    h-index

1–5