Progressive Pruning

Progressive Pruning is a model compression technique that iteratively removes redundant parameters or structures from a neural network in stages, gradually increasing sparsity while preserving performance, thereby distinguishing itself from one-shot pruning methods through its phased and adaptive refinement approach.

19

Publications

833

Citations

84

Authors

34

Institutions

Publications per year

2017–2026

14

Authors

84

  1. SL
    Sijia Liu

    Michigan State University, United States

    2 publications · 64 citations

    2

    h-index

  2. YW
    Yanzhi Wang

    Northeastern University, United States

    2 publications · 64 citations

    2

    h-index

  3. JP
    Jihong Pei

    Shenzhen University, China

    2 publications · 29 citations

    2

    h-index

  4. JT
    Jian Tang

    Syracuse University, United States

    2 publications · 64 citations

    2

    h-index

  5. TZ
    Tianyun Zhang

    Syracuse University, United States

    2 publications · 64 citations

    2

    h-index

1–5 of 84

Venues

  1. arXiv (Cornell University)

    Repository · 3 publications · 80 citations

    3

    h-index

  2. Neurocomputing

    2 publications · 85 citations

    2

    h-index

  3. 2

    h-index

  4. Information Sciences

    1 publications · 34 citations

    1

    h-index

  5. 2021 IEEE/CVF International Conference on Computer Vision (ICCV)

    Conference · 1 publications · 91 citations

    1

    h-index

1–5