EUVIMEDEUVIMED entdecken
Crossref

Heterogeneous Graph Embedding with Dual Edge Differentiation

Yuhong Chen, Fuhai Chen, Zhihao Wu, Zhaoliang Chen, Zhiling Cai, Yanchao Tan, Shiping Wang

Neural Networks · 2025-03 · 183 · 106965

DOI: 10.1016/j.neunet.2024.106965 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Neural Networks, 2025-03. Verfasst von Yuhong Chen und 6 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer and Data Science, Fuzhou University, Fuzhou 350116, China; Fujian Provincial Key Laboratory of Network Computing and Intelligent …. Hauptthemen laut MEDLINE: Datasets as Topic. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 54 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recently, heterogeneous graphs have attracted widespread attention as a powerful and practical superclass of traditional homogeneous graphs, which reflect the multi-type node entities and edge relations in the real world. Most existing methods adopt meta-path construction as the mainstream to learn long-range heterogeneous semantic messages between nodes. However, such schema constructs the node-wise correlation by connecting nodes via pre-computed fixed paths, which neglects the diversities of meta-paths on the path type and path range. In this paper, we propose a meta-path-based semantic embedding schema, which is called Heterogeneous Graph Embedding with Dual Edge Differentiation (HGE-DED) to adequately construct flexible meta-path combinations thus learning the rich and discriminative semantic of target nodes. Concretely, HGE-DED devises a Multi-Type and multi-Range Meta-Path Construction (MTR-MP Construction), which covers the comprehensive exploration of meta-path combinations from path type and path range, expressing the diversity of edges at more fine-grained scales. Moreover, HGE-DED designs the semantics and meta-path joint guidance, constructing a hierarchical short- and long-range relation adjustment, which constrains the path learning as well as minimizes the impact of edge heterophily on heterogeneous graphs. Experimental results on four benchmark datasets demonstrate the effectiveness of HGE-DED compared with state-of-the-art methods.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Datasets as TopicMachine LearningNeural Networks, ComputerSemantics

Stichwörter der Autor:innen

Graph neural networkHeterogeneous information networkMeta-path combinationSemantic embeddingSemi-supervised classification

Autor:innen und Institutionen

  • College of Computer and Data Science, Fuzhou University, Fuzhou 350116, China; Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing, Fuzhou University, Fuzhou 350116, China. Elect…
  • College of Computer and Information Science, Fujian Agriculture and Forestry University, Fuzhou 350002, China. Electronic address: zhilingcai@126.com.

Zitieren

APA

Chen, Y., Chen, F., Wu, Z., Chen, Z., Cai, Z., Tan, Y., & Wang, S. (2025). Heterogeneous Graph Embedding with Dual Edge Differentiation. Neural Networks, 183, 106965. https://doi.org/10.1016/j.neunet.2024.106965

Vancouver

Chen Y, Chen F, Wu Z, Chen Z, Cai Z, Tan Y, et al. Heterogeneous Graph Embedding with Dual Edge Differentiation. Neural Networks. 2025;183:106965. doi:10.1016/j.neunet.2024.106965

BibTeX
@article{Chen2025,
  author = {Chen, Yuhong and Chen, Fuhai and Wu, Zhihao and Chen, Zhaoliang and Cai, Zhiling and Tan, Yanchao and Wang, Shiping},
  title = {Heterogeneous Graph Embedding with Dual Edge Differentiation},
  journal = {Neural Networks},
  year = {2025},
  volume = {183},
  pages = {106965},
  doi = {10.1016/j.neunet.2024.106965}
}
Kostenlos starten →