Graph Neural Networks

Graph Neural Network is a type of neural network model that belongs to the broader class of deep learning architectures and is specifically designed to process and learn representations from graph-structured data by propagating and aggregating information across nodes and edges.

7.4K

Publications

636.2K

Citations

24.7K

Authors

3K

Institutions

Publications per year

2017–2026

7.3K

Authors

24.7K

  1. PS
    Philip S. Yu

    University of Illinois Chicago, United States

    64 publications · 6.8K citations

    33

    h-index

  2. SP
    Shirui Pan

    Monash University, Australia

    56 publications · 8.8K citations

    32

    h-index

  3. CS
    Chuan Shi

    Beijing University of Posts and Telecommunications, China

    52 publications · 6.9K citations

    32

    h-index

  4. JL
    Jure Leskovec

    Stanford University, United States

    46 publications · 7K citations

    31

    h-index

  5. XH
    Xiangnan He

    University of Science and Technology of China, China

    36 publications · 8.4K citations

    28

    h-index

1–5 of 24.7K

Venues

  1. arXiv (Cornell University)

    Repository · 1.2K publications · 90.8K citations

    120

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 253 publications · 34.2K citations

    79

    h-index

  3. 48

    h-index

  4. IEEE Transactions on Knowledge and Data Engineering

    TKDE · 114 publications · 10.5K citations

    47

    h-index

  5. IEEE Transactions on Pattern Analysis and Machine Intelligence

    TPAMI · 73 publications · 7.1K citations

    41

    h-index

1–5