Corpus ID: 227229005

A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources

  title={A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources},
  author={X. Wang and Deyu Bo and C. Shi and Shaohua Fan and Yanfang Ye and Philip S. Yu},
  • X. Wang, Deyu Bo, +3 authors Philip S. Yu
  • Published 2020
  • Computer Science
  • ArXiv
  • Heterogeneous graphs (HGs) also known as heterogeneous information networks have become ubiquitous in real-world scenarios; therefore, HG embedding, which aims to learn representations in a lower-dimension space while preserving the heterogeneous structures and semantics for downstream tasks (e.g., node/graph classification, node clustering, link prediction), has drawn considerable attentions in recent years. In this survey, we perform a comprehensive review of the recent development on HG… CONTINUE READING
    2 Citations

    Figures and Tables from this paper

    Beyond Low-frequency Information in Graph Convolutional Networks
    • PDF


    mg2vec: Learning Relationship-Preserving Heterogeneous Graph Representations via Metagraph Embedding
    • 4
    • PDF
    A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications
    • 684
    • PDF
    Graph Embedding Techniques, Applications, and Performance: A Survey
    • 739
    • PDF
    Heterogeneous Graph Neural Network
    • 127
    • Highly Influential
    • PDF
    AspEm: Embedding Learning by Aspects in Heterogeneous Information Networks
    • 49
    • Highly Influential
    • PDF
    Are Meta-Paths Necessary?: Revisiting Heterogeneous Graph Embeddings
    • 36
    • Highly Influential
    • PDF
    An Attention-based Graph Neural Network for Heterogeneous Structural Learning
    • 8
    • PDF
    Network Schema Preserving Heterogeneous Information Network Embedding
    • 2
    • PDF