Concepedia

Model Compression For Continual Learning

Model Compression for Continual Learning is a methodological framework that belongs to the class of continual learning techniques, distinguished by its focus on reducing the memory and computational footprint of neural models through mechanisms such as pruning, quantization, or knowledge distillation while preserving previously acquired knowledge during sequential task learning.

24

Publications

1.8K

Citations

105

Authors

42

Institutions

Publications per year

2017–2026

23

Parents

Publications

24

A comprehensive survey on model compression and acceleration

Tejalal Choudhary, Vipul Kumar Mishra, Anurag Goswami et al. · Artificial Intelligence Review · 2020 · 504 citations

, , +14

Progress & Compress: A scalable framework for continual learning

Jonathan Schwarz, Jelena Luketina, Wojciech Marian Czarnecki et al. · arXiv (Cornell University) · 2018 · 293 citations · Full text

, , +16

Dynamic Network Surgery for Efficient DNNs

Yiwen Guo, Anbang Yao, Yurong Chen · arXiv (Cornell University) · 2016 · 140 citations · Full text

, , +16

Compacting, Picking and Growing for Unforgetting Continual Learning

Steven C. Y. Hung, Cheng-Hao Tu, Cheng‐En Wu et al. · arXiv (Cornell University) · 2019 · 134 citations · Full text

, , +10

Train Big, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers

Zhuohan Li, Eric Wallace, Sheng Shen et al. · International Conference on Machine Learning · 2020 · 111 citations

, , +11

1–5 of 24

Authors

105

  1. PH
    Pengcheng He

    Microsoft Research (United Kingdom), United Kingdom

    2 publications · 54 citations

    2

    h-index

  2. CW
    Cheng‐En Wu

    National Yang Ming Chiao Tung University, Taiwan

    2 publications · 206 citations

    2

    h-index

  3. YC
    Yi-Ming Chan

    National University of Kaohsiung, Taiwan

    2 publications · 206 citations

    2

    h-index

  4. CC
    Chien‐Hung Chen

    National Taiwan University, Taiwan

    2 publications · 206 citations

    2

    h-index

  5. WC
    Weizhu Chen

    Microsoft (United States), United States

    2 publications · 54 citations

    2

    h-index

1–5 of 105

Institutions

42

  1. Arizona State University

    Tempe, United States

    2 h-index

    7 publications

    98 citations

  2. ETH Zurich

    Zurich, Switzerland

    2 h-index

    5 publications

    138 citations

  3. Microsoft Research (United Kingdom)

    Cambridge, United Kingdom

    1 h-index

    1 publications

    40 citations

  4. State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing

    Wuhan, China

    1 h-index

    2 publications

    114 citations

  5. Bangalore University

    Bengaluru, India

    1 h-index

    1 publications

    20 citations

  6. Scuola Normale Superiore

    Pisa, Italy

    1 h-index

    1 publications

    32 citations

  7. Center for Excellence in Brain Science and Intelligence Technology

    Shanghai, China

    1 h-index

    1 publications

    25 citations

  8. Jiangsu University

    Zhenjiang, China

    1 h-index

    1 publications

    50 citations

1–8 of 42

Venues

  1. arXiv (Cornell University)

    Repository · 8 publications · 712 citations

    8

    h-index

  2. Neurocomputing

    2 publications · 79 citations

    2

    h-index

  3. 2022 International Joint Conference on Neural Networks (IJCNN)

    Conference · 1 publications · 32 citations

    1

    h-index

  4. Frontiers in Artificial Intelligence

    1 publications · 15 citations

    1

    h-index

  5. Bioinformatics

    1 publications · 40 citations

    1

    h-index

1–5