Metric-based Meta-learning

Metric-Based Meta-Learning is a meta-learning approach that belongs to the class of methods leveraging learned distance metrics to compare task-specific representations, distinguished by its reliance on a parameterized metric space to generalize across tasks by measuring similarity between support and query examples.

55

Publications

6.5K

Citations

203

Authors

92

Institutions

Publications per year

2017–2026

51

Authors

203

  1. MY
    Mo Yu

    IBM (United States), United States

    4 publications · 343 citations

    4

    h-index

  2. XG
    Xiaoxiao Guo

    IBM (United States), United States

    4 publications · 343 citations

    4

    h-index

  3. YC
    Yu Cheng

    Tsinghua University, China

    3 publications · 323 citations

    3

    h-index

  4. BZ
    Bowen Zhou

    IBM (United States), United States

    3 publications · 278 citations

    3

    h-index

  5. JY
    Jinfeng Yi

    Jingdong (China), China

    2 publications · 258 citations

    2

    h-index

1–5 of 203

Venues

  1. arXiv (Cornell University)

    Repository · 4 publications · 109 citations

    4

    h-index

  2. 2

    h-index

  3. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 2 publications · 66 citations

    2

    h-index

  4. Measurement Science and Technology

    2 publications · 176 citations

    2

    h-index

  5. ArXiv.org

    Repository · 2 publications · 754 citations

    2

    h-index

1–5