Concepedia

Pruning During Pre-training

Pruning During Pre-Training is a model compression strategy that belongs to the class of pruning methods, differing in that it specifically involves the removal of redundant or less important parameters directly within the pre-training phase of deep learning models, rather than after pre-training or during fine-tuning.

100

Publications

10.3K

Citations

352

Authors

112

Institutions

Publications per year

2017–2026

92

Parents

Publications

100

The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks

Jonathan Frankle, Michael Carbin · arXiv (Cornell University) · 2018 · 1.3K citations · Full text

, , +12

Pruning Convolutional Neural Networks for Resource Efficient Inference

Pavlo Molchanov, Stephen Tyree, Tero Karras et al. · arXiv (Cornell University) · 2016 · 1.2K citations · Full text

, , +16

Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks

Yang He, Guoliang Kang, Xuanyi Dong et al. · 2018 · 989 citations · Full text

, , +15

Rethinking the Value of Network Pruning

Zhuang Liu, Mingjie Sun, Tinghui Zhou et al. · arXiv (Cornell University) · 2018 · 744 citations · Full text

, , +10

The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks.

Jonathan Frankle, Michael Carbin · DSpace@MIT (Massachusetts Institute of Technology) · 2019 · 736 citations · Full text

, , +12

1–5 of 100

Authors

352

  1. PM
    Pavlo Molchanov

    Nvidia (United States), United States

    4 publications · 1.8K citations

    4

    h-index

  2. NL
    Namhoon Lee

    Anyang University, South Korea

    3 publications · 657 citations

    3

    h-index

  3. GK
    Guoliang Kang

    University of Technology Sydney, Australia

    3 publications · 1.2K citations

    3

    h-index

  4. TK
    Tero Karras

    Nvidia (United Kingdom), United Kingdom

    3 publications · 1.8K citations

    3

    h-index

  5. XD
    Xuanyi Dong

    University of Technology Sydney, Australia

    3 publications · 1.2K citations

    3

    h-index

1–5 of 352

Institutions

112

  1. Tsinghua University

    Beijing, China

    8 h-index

    23 publications

    2K citations

  2. Massachusetts Institute of Technology

    Cambridge, United States

    6 h-index

    8 publications

    4.2K citations

  3. University of Science and Technology of China

    Hefei, China

    4 h-index

    10 publications

    370 citations

  4. Zhejiang University

    Hangzhou, China

    3 h-index

    10 publications

    255 citations

  5. University of Chinese Academy of Sciences

    Beijing, China

    3 h-index

    7 publications

    221 citations

  6. Princeton University

    Princeton, United States

    3 h-index

    5 publications

    280 citations

  7. Universidad del Noreste

    Tampico, Mexico

    3 h-index

    8 publications

    412 citations

  8. Fudan University

    Shanghai, China

    3 h-index

    3 publications

    1.2K citations

1–8 of 112

Venues

  1. arXiv (Cornell University)

    Repository · 32 publications · 5.1K citations

    21

    h-index

  2. Neurocomputing

    4 publications · 95 citations

    4

    h-index

  3. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 4 publications · 176 citations

    4

    h-index

  4. 4

    h-index

  5. Applied Soft Computing

    3 publications · 64 citations

    3

    h-index

1–5