EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Aligning entity of knowledge graph based on graph convolutional network with maximum translated similarity

Jianhui Zhou iD, Yun Gao, Xiangbing Zhao, Yanping Guo, Xulong Zhang

PLOS One · 06.11.2026 · 21 (11) · e0362390

DOI: 10.1371/journal.pone.0362390 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 06.11.2026. Verfasst von Jianhui Zhou und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer and Network Engineering, Shanxi Datong University, Datong, China. Die Arbeit nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Research and Development Program of Datong City, Science and Technology Research Special Fund of Taihang Laboratory In Shanxi Province, Application Basic Research Project of Datong City.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Entity alignment is a pivotal technology for integrating heterogeneous knowledge graphs, yet most embedding-based alignment methods destroy the inherent structural embedding information of knowledge graphs when unifying cross-graph embedding spaces, resulting in limited alignment accuracy and stability. To tackle this issue, this paper proposes a novel model for entity alignment tasks, which named as Graph Convolutional Network with Maximum Translated Similarity (GCN-MTS). GCN-MTS innovatively leverages a maximum translated similarity mechanism to optimize the adjacency matrix, degree matrix and loss function. This core design effectively maintains the original relative embedding structure of cross-graph entities during embedding space unification, which is the key improvement over existing approaches. Comprehensive experiments on 3 pairs of real-world knowledge graph dataset demonstrate the superior performance of GCN-MTS against advanced baseline methods. It achieves average performance gains of 5%–15% in Hits@1 and 4%–16% in Hits@10. Ablation results confirm that the optimized module brings a nearly 22% improvement in alignment metrics compared with the vanilla GCN. Furthermore, GCN-MTS presents excellent robustness and stability across different seed alignment quantities and seed combinations.

Autor:innen und Institutionen

  • School of Computer and Network Engineering, Shanxi Datong University, Datong, China.

ORCID-Profile: Jianhui Zhou

Förderung

  • Key Research and Development Program of Datong City
  • Science and Technology Research Special Fund of Taihang Laboratory In Shanxi Province
  • Application Basic Research Project of Datong City

Zitieren

APA

Zhou, J., Gao, Y., Zhao, X., Guo, Y., & Zhang, X. (2026). Aligning entity of knowledge graph based on graph convolutional network with maximum translated similarity. PLOS One, 21(11), e0362390. https://doi.org/10.1371/journal.pone.0362390

Vancouver

Zhou J, Gao Y, Zhao X, Guo Y, Zhang X. Aligning entity of knowledge graph based on graph convolutional network with maximum translated similarity. PLOS One. 2026;21(11):e0362390. doi:10.1371/journal.pone.0362390

BibTeX
@article{Zhou2026,
  author = {Zhou, Jianhui and Gao, Yun and Zhao, Xiangbing and Guo, Yanping and Zhang, Xulong},
  title = {Aligning entity of knowledge graph based on graph convolutional network with maximum translated similarity},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {11},
  pages = {e0362390},
  doi = {10.1371/journal.pone.0362390}
}
Kostenlos starten →