Graph Convolutional Networks

Graph Convolutional Networks is a type of neural network model designed for graph-structured data that generalizes convolutional operations to non-Euclidean domains by propagating and aggregating node features through localized spectral filtering over the graph topology.

3.9K

Publications

331.8K

Citations

13.6K

Authors

2.2K

Institutions

Publications per year

2017–2026

3.9K

Variants

Graph Convolutional Network

Authors

13.6K

  1. MM
    Michael M. Bronstein

    Università della Svizzera italiana, Switzerland

    18 publications · 8.3K citations

    17

    h-index

  2. JH
    Junzhou Huang

    The University of Texas at Arlington, United States

    18 publications · 3.5K citations

    16

    h-index

  3. SP
    Shirui Pan

    Monash University, Australia

    18 publications · 1.8K citations

    16

    h-index

  4. BY
    Baocai Yin

    Beijing University of Technology, China

    16 publications · 1.1K citations

    15

    h-index

  5. XH
    Xiangnan He

    University of Science and Technology of China, China

    16 publications · 1.5K citations

    15

    h-index

1–5 of 13.6K

Venues

  1. arXiv (Cornell University)

    Repository · 400 publications · 34.3K citations

    75

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 127 publications · 29.2K citations

    63

    h-index

  3. 41

    h-index

  4. 36

    h-index

  5. 34

    h-index

1–5