Graph Neural Network Features

Graph Neural Network Features is a computational construct that represents node, edge, or graph-level attributes derived through message-passing mechanisms in graph neural networks to encode structural and feature information for downstream learning tasks.

506

Publications

36.2K

Citations

2.2K

Authors

626

Institutions

Publications per year

2017–2026

504

Authors

2.2K

  1. XL
    Xiaorui Liu

    Michigan State University, United States

    5 publications · 726 citations

    5

    h-index

  2. JL
    Jure Leskovec

    Stanford University, United States

    5 publications · 977 citations

    5

    h-index

  3. KK
    Kris Kitani

    Carnegie Mellon University, United States

    5 publications · 580 citations

    5

    h-index

  4. PL
    Pan Li

    Purdue University West Lafayette, United States

    5 publications · 270 citations

    5

    h-index

  5. JT
    Jiliang Tang

    Michigan State University, United States

    5 publications · 726 citations

    5

    h-index

1–5 of 2.2K

Venues

  1. arXiv (Cornell University)

    Repository · 71 publications · 4.1K citations

    28

    h-index

  2. IEEE Access

    12 publications · 536 citations

    12

    h-index

  3. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 11 publications · 2.7K citations

    11

    h-index

  4. 10

    h-index

  5. Briefings in Bioinformatics

    9 publications · 633 citations

    9

    h-index

1–5