EUVIMEDEUVIMED entdecken
Crossref

SGKGE: Semantically Guided Knowledge Graph Embeddings via Complementary Latent Representations

Ruizhou Liu, Zongsheng Cao, Zhe Wu, Yiling Wu, Qianqian Xu, Qingming Huang

IEEE Transactions on Neural Networks and Learning Systems · 2025-06 · 36 (6) · 10114-10127

DOI: 10.1109/tnnls.2025.3545773 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Neural Networks and Learning Systems, 2025-06. Verfasst von Ruizhou Liu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 70 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Knowledge graph (KG) completion is a challenging yet essential task that has attracted increasing attention in recent years. While entities in KGs typically present complex semantics (a phenomenon known as polysemy), previous works primarily focus on holistic but often inaccurate representations of entities, neglecting the diversity of their semantics. This limitation results in suboptimal representations for entities within KGs. To address this issue, we propose a new method termed semantically guided KG embeddings (SGKGE), which captures the precise semantics of entities in KGs from a semantics-guided perspective. Specifically, SGKGE first guides the learning of holistic semantics of entities through a hyperbolic manifold with learnable shared curvature and a geometric attention-fusion module, facilitating efficient reasoning. Subsequently, SGKGE captures fine-grained semantics through a set of Cartesian product Riemannian manifolds with distinct curvatures, coupled with a semantic interactions module. This approach enables SGKGE to produce more accurate entity semantics and enhance downstream applications. Experimental results demonstrate that our model achieves state-of-the-art performance on six well-established KG completion benchmarks. The release code is available at https://github.com/RuizhouLiu/SGKGE.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Liu, R., Cao, Z., Wu, Z., Wu, Y., Xu, Q., & Huang, Q. (2025). SGKGE: Semantically Guided Knowledge Graph Embeddings via Complementary Latent Representations. IEEE Transactions on Neural Networks and Learning Systems, 36(6), 10114-10127. https://doi.org/10.1109/tnnls.2025.3545773

Vancouver

Liu R, Cao Z, Wu Z, Wu Y, Xu Q, Huang Q. SGKGE: Semantically Guided Knowledge Graph Embeddings via Complementary Latent Representations. IEEE Transactions on Neural Networks and Learning Systems. 2025;36(6):10114-10127. doi:10.1109/tnnls.2025.3545773

BibTeX
@article{Liu2025,
  author = {Liu, Ruizhou and Cao, Zongsheng and Wu, Zhe and Wu, Yiling and Xu, Qianqian and Huang, Qingming},
  title = {SGKGE: Semantically Guided Knowledge Graph Embeddings via Complementary Latent Representations},
  journal = {IEEE Transactions on Neural Networks and Learning Systems},
  year = {2025},
  volume = {36},
  number = {6},
  pages = {10114--10127},
  doi = {10.1109/tnnls.2025.3545773}
}
Kostenlos starten →