Graph Few-shot Learning

Graph Few-Shot Learning is a specialized learning paradigm in graph-based machine learning that enables the generalization to new tasks or classes with limited labeled graph data by leveraging prior knowledge from related graph-structured tasks.

67

Publications

3.4K

Citations

240

Authors

99

Institutions

Publications per year

2017–2026

67

Authors

240

  1. KD
    Kaize Ding

    Arizona State University, United States

    6 publications · 319 citations

    6

    h-index

  2. CZ
    Chuxu Zhang

    University of Notre Dame, United States

    4 publications · 357 citations

    4

    h-index

  3. HL
    Huan Liu

    Arizona State University, United States

    4 publications · 206 citations

    4

    h-index

  4. JL
    Jundong Li

    University of Virginia, United States

    3 publications · 112 citations

    4

    h-index

  5. YF
    Yuan Fang

    Singapore Management University, Singapore

    3 publications · 153 citations

    3

    h-index

1–5 of 240

Venues

  1. arXiv (Cornell University)

    Repository · 8 publications · 629 citations

    8

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 4 publications · 308 citations

    4

    h-index

  3. Neural Networks

    3 publications · 123 citations

    3

    h-index

  4. 2

    h-index

  5. IEEE Transactions on Image Processing

    2 publications · 47 citations

    2

    h-index

1–5