Memory-augmented Meta-learning

Memory-Augmented Meta-Learning is a meta-learning framework that incorporates an explicit, external memory component to store and retrieve task-specific knowledge, thereby enhancing rapid adaptation to new tasks through improved information retention and generalization across episodes.

10

Publications

1.2K

Citations

53

Authors

23

Institutions

Publications per year

2017–2026

9

Authors

53

  1. YL
    Yaojin Lin

    Minnan Normal University, China

    2 publications · 248 citations

    2

    h-index

  2. SL
    Shaozi Li

    Xiamen University, China

    2 publications · 248 citations

    2

    h-index

  3. FY
    Fengxiang Yang

    Xiamen University, China

    2 publications · 248 citations

    2

    h-index

  4. ZL
    Zhiming Luo

    Xiamen University, China

    2 publications · 248 citations

    2

    h-index

  5. ZZ
    Zhun Zhong

    University of Trento, Italy

    2 publications · 248 citations

    2

    h-index

1–5 of 53

Venues

  1. arXiv (Cornell University)

    Repository · 4 publications · 705 citations

    4

    h-index

  2. World Wide Web

    1 publications · 18 citations

    1

    h-index

  3. Connection Science

    1 publications · 19 citations

    1

    h-index

  4. Neuron

    1 publications · 55 citations

    1

    h-index

  5. International Conference on Machine Learning

    Conference · 1 publications · 125 citations

    1

    h-index

1–5