Model-agnostic Meta-learning

Model-Agnostic Meta-Learning is a meta-learning algorithm that enables rapid adaptation to new tasks by optimizing model parameters such that fine-tuning from those parameters via gradient descent yields fast and effective learning across a diverse range of models and architectures.

207

Publications

19.4K

Citations

725

Authors

258

Institutions

Publications per year

2017–2026

207

Authors

725

  1. AM
    Aryan Mokhtari

    University of Pennsylvania, United States

    7 publications · 878 citations

    7

    h-index

  2. CF
    Chelsea Finn

    University of California, Berkeley, United States

    6 publications · 6.9K citations

    6

    h-index

  3. AF
    Alireza Fallah

    Massachusetts Institute of Technology, United States

    5 publications · 853 citations

    5

    h-index

  4. AO
    Asuman Ozdaglar

    Massachusetts Institute of Technology, United States

    5 publications · 853 citations

    5

    h-index

  5. SL
    Sergey Levine

    University of California, Berkeley, United States

    4 publications · 6.8K citations

    4

    h-index

1–5 of 725

Venues

  1. arXiv (Cornell University)

    Repository · 44 publications · 9.4K citations

    24

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 5 publications · 1.3K citations

    5

    h-index

  3. IEEE Transactions on Industrial Informatics

    4 publications · 368 citations

    4

    h-index

  4. IEEE Access

    3 publications · 71 citations

    3

    h-index

  5. 2021 IEEE/CVF International Conference on Computer Vision (ICCV)

    Conference · 3 publications · 208 citations

    3

    h-index

1–5