Concepedia

Hard Parameter Sharing

Hard Parameter Sharing is a multi-task learning strategy in which the majority of model parameters are shared across all tasks, while only task-specific layers remain private, thereby enabling inductive transfer through constrained parameter allocation.

28

Publications

2.5K

Citations

119

Authors

50

Institutions

Publications per year

2017–2026

28

Parents

Publications

28

Efficient Neural Architecture Search via Parameters Sharing

Hieu Pham, Melody Y. Guan, Barret Zoph et al. · International Conference on Machine Learning · 2018 · 1.3K citations

, , +13

Learning Sparse Sharing Architectures for Multiple Tasks

Tianxiang Sun, Yunfan Shao, Xiaonan Li et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 2020 · 136 citations · Full text

, , +11

Sluice networks: Learning what to share between loosely related tasks.

Sebastian Ruder, Joachim Bingel, Isabelle Augenstein et al. · arXiv (Cornell University) · 2017 · 118 citations · Full text

, , +14

Multi-Task Learning With Coarse Priors for Robust Part-Aware Person Re-Identification

Changxing Ding, Kan Wang, Pengfei Wang et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2020 · 100 citations · Full text

, , +16

Deep $k$-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions

Junru Wu, Yue Wang, Zhenyu Wu et al. · arXiv (Cornell University) · 2018 · 84 citations · Full text

, , +16

1–5 of 28

Authors

119

  1. AS
    Anders Søgaard

    University of Copenhagen, Denmark

    3 publications · 220 citations

    3

    h-index

  2. ZW
    Zhangyang Wang

    The University of Texas at Austin, United States

    2 publications · 104 citations

    2

    h-index

  3. YS
    Yunfan Shao

    Fudan University, China

    2 publications · 153 citations

    2

    h-index

  4. AS
    Aaqib Saeed

    Eindhoven University of Technology, Netherlands

    2 publications · 41 citations

    2

    h-index

  5. SR
    Sebastian Ruder

    Google (United States), United States

    2 publications · 186 citations

    2

    h-index

1–5 of 119

Institutions

50

  1. Fudan University

    Shanghai, China

    2 h-index

    12 publications

    918 citations

  2. Tianjin University

    Tianjin, China

    2 h-index

    9 publications

    451 citations

  3. Stanford University

    Stanford, United States

    2 h-index

    6 publications

    1.4K citations

  4. Xidian University

    Xi'an, China

    2 h-index

    2 publications

    153 citations

  5. Aerospace Information Research Institute

    Beijing, China

    1 h-index

    5 publications

    95 citations

  6. University of Freiburg

    Freiburg im Breisgau, Germany

    1 h-index

    3 publications

    78 citations

  7. University of British Columbia

    Vancouver, Canada

    1 h-index

    1 publications

    67 citations

  8. Intel (United States)

    Santa Clara, United States

    1 h-index

    1 publications

    13 citations

1–8 of 50

Venues

  1. arXiv (Cornell University)

    Repository · 6 publications · 269 citations

    6

    h-index

  2. International Conference on Machine Learning

    Conference · 2 publications · 1.3K citations

    2

    h-index

  3. 2

    h-index

  4. TUbilio (Technical University of Darmstadt)

    Repository · 1 publications · 11 citations

    1

    h-index

  5. Sensors

    1 publications · 27 citations

    1

    h-index

1–5