Relation Structure-Aware Heterogeneous Graph Neural Network

Shichao Zhu, Chuan Zhou, Shirui Pan, Xingquan Zhu, Bin Wang

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

3 Citations (Scopus)

Abstract

Heterogeneous graphs with different types of nodes and edges are ubiquitous and have immense value in many applications. Existing works on modeling heterogeneous graphs usually follow the idea of splitting a heterogeneous graph into multiple homogeneous subgraphs. This is ineffective in exploiting hidden rich semantic associations between different types of edges for large-scale multi-relational graphs. In this paper, we propose Relation Structure-Aware Heterogeneous Graph Neural Network (RSHN), a unified model that integrates graph and its coarsened line graph to embed both nodes and edges in heterogeneous graphs without requiring any prior knowledge such as metapath. To tackle the heterogeneity of edge connections, RSHN first creates a Coarsened Line Graph Neural Network (CL-GNN) to excavate edge-centric relation structural features that respect the latent associations of different types of edges based on coarsened line graph. After that, a Heterogeneous Graph Neural Network (H-GNN) is used to leverage implicit messages from neighbor nodes and edges propagating among nodes in heterogeneous graphs. As a result, different types of nodes and edges can enhance their embedding through mutual integration and promotion. Experiments and comparisons, based on semi-supervised classification tasks on large scale heterogeneous networks with over a hundred types of edges, show that RSHN significantly outperforms state-of-the-arts.

Original languageEnglish
Title of host publicationProceedings - 19th IEEE International Conference on Data Mining, ICDM 2019
EditorsJianyong Wang, Kyuseok Shim, Xindong Wu
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages1534-1539
Number of pages6
ISBN (Electronic)9781728146034, 9781728146041
ISBN (Print)9781728146058
DOIs
Publication statusPublished - 2019
EventIEEE International Conference on Data Mining 2019 - Beijing, China
Duration: 8 Nov 201911 Nov 2019
Conference number: 19th
http://icdm2019.bigke.org/

Publication series

NameIEEE, Institute of Electrical and Electronics Engineers
PublisherIEEE, Institute of Electrical and Electronics Engineers
Volume2019-November
ISSN (Print)1550-4786
ISSN (Electronic)2374-8486

Conference

ConferenceIEEE International Conference on Data Mining 2019
Abbreviated titleICDM 2019
CountryChina
CityBeijing
Period8/11/1911/11/19
Internet address

Keywords

  • Coarsened line graph
  • Graph neural network
  • Heterogenous graph

Cite this