Multi-task Learning Theory

Multi-Task Learning Theory is a formal theoretical framework that characterizes the principles and mechanisms underlying the joint optimization of multiple related learning tasks, distinguishing itself by modeling shared representations, task relationships, and inductive biases to improve generalization across tasks.

213

Publications

17.6K

Citations

740

Authors

276

Institutions

Publications per year

2017–2026

147

Authors

740

  1. MP
    Massimiliano Pontil

    University College London, United Kingdom

    6 publications · 732 citations

    6

    h-index

  2. CA
    Charles A. Micchelli

    IBM Research - Thomas J. Watson Research Center, United States

    4 publications · 604 citations

    4

    h-index

  3. YZ
    Yu Zhang

    Hong Kong University of Science and Technology, Hong Kong SAR China

    3 publications · 2.8K citations

    3

    h-index

  4. JH
    Jizhou Huang

    Baidu (China), China

    3 publications · 202 citations

    3

    h-index

  5. FB
    Francis Bach

    Institut national de recherche en sciences et technologies du numérique, France

    3 publications · 477 citations

    3

    h-index

1–5 of 740

Venues

  1. arXiv (Cornell University)

    Repository · 27 publications · 2.9K citations

    18

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 5 publications · 334 citations

    5

    h-index

  3. IEEE Access

    4 publications · 197 citations

    4

    h-index

  4. 3

    h-index

  5. 3

    h-index

1–5