Heterogeneous Graph Learning

Heterogeneous Graph Learning is a graph-based learning paradigm that extends conventional graph models to handle heterogeneous graphs by incorporating multiple node and edge types, enabling the representation and inference of complex relational structures across diverse entity and relation categories.

476

Publications

32.9K

Citations

2K

Authors

431

Institutions

Publications per year

2017–2026

462

Authors

2K

  1. CS
    Chuan Shi

    Beijing University of Posts and Telecommunications, China

    21 publications · 5.2K citations

    18

    h-index

  2. PS
    Philip S. Yu

    University of Illinois Chicago, United States

    22 publications · 4.5K citations

    18

    h-index

  3. HP
    Hao Peng

    Beihang University, China

    12 publications · 791 citations

    12

    h-index

  4. XW
    Xiao Wang

    Beijing University of Posts and Telecommunications, China

    12 publications · 1.4K citations

    11

    h-index

  5. CH
    Chao Huang

    University of Hong Kong, Hong Kong SAR China

    9 publications · 2.2K citations

    9

    h-index

1–5 of 2K

Venues

  1. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 26 publications · 2.4K citations

    25

    h-index

  2. Knowledge-Based Systems

    23 publications · 906 citations

    17

    h-index

  3. arXiv (Cornell University)

    Repository · 27 publications · 1.2K citations

    17

    h-index

  4. Expert Systems with Applications

    14 publications · 436 citations

    14

    h-index

  5. Briefings in Bioinformatics

    12 publications · 820 citations

    12

    h-index

1–5