Late Pruning

Late Pruning is a pruning strategy in machine learning model optimization that belongs to the category of structured sparsity methods, distinguished by its execution phase occurring after the completion of the training process, thereby removing redundant parameters based on post-training saliency analysis.

13

Publications

305

Citations

43

Authors

20

Institutions

Publications per year

2017–2026

9

Variants

Post-training Pruning

Authors

43

  1. VO
    Víctor O. Sadras

    South Australian Research and Development Institute, Australia

    3 publications · 100 citations

    3

    h-index

  2. MM
    Martin Moran

    South Australian Research and Development Institute, Australia

    3 publications · 100 citations

    3

    h-index

  3. PR
    Paul R. Petrie

    South Australian Research and Development Institute, Australia

    3 publications · 100 citations

    3

    h-index

  4. MH
    Matanya Harel

    Ariel University, Israel

    2 publications · 27 citations

    2

    h-index

  5. AF
    Aaron Fait

    Ben-Gurion University of the Negev, Israel

    2 publications · 27 citations

    2

    h-index

1–5 of 43

Venues

  1. Australian Journal of Grape and Wine Research

    6 publications · 176 citations

    6

    h-index

  2. HortScience

    1 publications · 18 citations

    1

    h-index

  3. Frontiers in Plant Science

    1 publications · 14 citations

    1

    h-index

  4. American Journal of Enology and Viticulture

    AJEV · 1 publications · 28 citations

    1

    h-index

  5. 1

    h-index

1–5