Graph Explainability

Graph Explainability is a methodological framework within graph-based learning that enables the interpretation and justification of predictions made by graph neural networks by revealing the contribution of graph structures and node features to model decisions.

123

Publications

8.4K

Citations

484

Authors

183

Institutions

Publications per year

2017–2026

115

Authors

484

  1. MŽ
    Marinka Žitnik

    Harvard University, United States

    5 publications · 949 citations

    5

    h-index

  2. AZ
    An Zhang

    National University of Singapore, Singapore

    4 publications · 105 citations

    4

    h-index

  3. XH
    Xiangnan He

    University of Science and Technology of China, China

    4 publications · 105 citations

    4

    h-index

  4. TC
    Tat‐Seng Chua

    National University of Singapore, Singapore

    4 publications · 105 citations

    4

    h-index

  5. SW
    Suhang Wang

    Pennsylvania State University, United States

    4 publications · 222 citations

    4

    h-index

1–5 of 484

Venues

  1. arXiv (Cornell University)

    Repository · 32 publications · 2K citations

    20

    h-index

  2. 4

    h-index

  3. 4

    h-index

  4. 4

    h-index

  5. Neurocomputing

    2 publications · 55 citations

    2

    h-index

1–5