EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-view Heterogeneous Graph Neural Networks for Node Classification

Xi Zeng, Fang-Yuan Lei, Chang-Dong Wang, Qing-Yun Dai

Data Science and Engineering · 2024-09 · 9 (3) · 294-308

DOI: 10.1007/s41019-024-00253-y ↗

Kurz gefasst

Fachartikel in der Zeitschrift Data Science and Engineering, online erschienen am 24.06.2024. Verfasst von Xi Zeng und 3 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guangdong Provincial Key Laboratory of Intellectual Property and Big Data.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recently, with graph neural networks (GNNs) becoming a powerful technique for graph representation, many excellent GNN-based models have been proposed for processing heterogeneous graphs, which are termed Heterogeneous graph neural networks (HGNNs). However, existing HGNNs tend to aggregate information from either direct neighbors or those connected by short metapaths, thereby neglecting the higher-order information and global feature similarity information in heterogeneous graphs. In this paper, we propose a Multi-View Heterogeneous graph neural network (MV-HGNN) to aggregate these information. Firstly, two auxiliary views, specifically a global feature similarity view and a graph diffusion view, are generated from the original heterogeneous graph. Secondly, MV-HGNN performs two message-passing strategies to get the representation of different views. Subsequently, a transformer-based aggregator is used to get the semantic information. Subsequently, the representations of the three views are fused into a final composite representation. We evaluate our method on the node classification task over three commonly used heterogeneous graph datasets, and the results demonstrate that our proposed MV-HGNN significantly outperforms state-of-the-art baselines.

Förderung

  • Guangdong Provincial Key Laboratory of Intellectual Property and Big Data

Zitieren

APA

Zeng, X., Lei, F., Wang, C., & Dai, Q. (2024). Multi-view Heterogeneous Graph Neural Networks for Node Classification. Data Science and Engineering, 9(3), 294-308. https://doi.org/10.1007/s41019-024-00253-y

Vancouver

Zeng X, Lei F, Wang C, Dai Q. Multi-view Heterogeneous Graph Neural Networks for Node Classification. Data Science and Engineering. 2024;9(3):294-308. doi:10.1007/s41019-024-00253-y

BibTeX
@article{Zeng2024,
  author = {Zeng, Xi and Lei, Fang-Yuan and Wang, Chang-Dong and Dai, Qing-Yun},
  title = {Multi-view Heterogeneous Graph Neural Networks for Node Classification},
  journal = {Data Science and Engineering},
  year = {2024},
  volume = {9},
  number = {3},
  pages = {294--308},
  doi = {10.1007/s41019-024-00253-y}
}
Kostenlos starten →