Sparse Multi-task Learning

Sparse Multi-Task Learning is a multi-task learning framework that enforces sparsity in the shared representation or parameter structure to simultaneously promote model simplicity and task-specific feature selection by identifying and leveraging only the most relevant parameters across related tasks.

86

Publications

6.2K

Citations

285

Authors

133

Institutions

Publications per year

2017–2026

44

Authors

285

  1. AJ
    Andrew J. Saykin

    Indiana University – Purdue University Indianapolis, United States

    8 publications · 510 citations

    8

    h-index

  2. LS
    Li Shen

    Indiana University – Purdue University Indianapolis, United States

    8 publications · 510 citations

    8

    h-index

  3. SL
    Shannon L. Risacher

    Indiana University – Purdue University Indianapolis, United States

    7 publications · 482 citations

    7

    h-index

  4. DS
    Dinggang Shen

    University of North Carolina at Chapel Hill, United States

    5 publications · 498 citations

    5

    h-index

  5. KL
    Kefei Liu

    University of Pennsylvania, United States

    5 publications · 213 citations

    5

    h-index

1–5 of 285

Venues

  1. arXiv (Cornell University)

    Repository · 6 publications · 327 citations

    6

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 5 publications · 325 citations

    5

    h-index

  3. IEEE Transactions on Cybernetics

    4 publications · 411 citations

    4

    h-index

  4. Bioinformatics

    4 publications · 285 citations

    4

    h-index

  5. Pattern Recognition

    3 publications · 137 citations

    3

    h-index

1–5