AttenE: A knowledge graph completion model based on entity-relation attention embedding
International Journal of Modern Physics C · 2026-06 · 37 (06)
DOI: 10.1142/s0129183125420185 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Modern Physics C, online erschienen am 23.08.2025. Verfasst von Xuepeng Mou und 9 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 38 Literaturangaben. Gefördert von: the Science and Technology Project of China Southern Power Grid Co. Ltd., the Special Fund for the Central Government to Guide Local Science, the Key Research and Development Program of Yunnan Province.
Abstract (Originalsprache)
Knowledge graphs, as a structured form of knowledge representation, have been widely applied in various fields such as recommendation systems, intelligent question answering, big data decision-making and the Internet of things. However, due to the diversity of data sources and limitations in construction methods, knowledge graphs often suffer from significant information loss, which severely affects their completeness and application effectiveness. To address this, the task of knowledge graph completion has emerged, aiming to improve the knowledge graph by predicting missing entities or relationships. In recent years, although convolutional neural network-based methods have made some progress in the field of knowledge graph completion, these methods still have limitations in capturing the interaction features between entities and relationships. To overcome this, we propose a knowledge graph completion model based on entity-relationship attention embedding, called AttenE. The model introduces an attention mechanism that can deeply capture the complex interaction features between entities and relationships, generating highly expressive feature representations. Specifically, the AttenE model extracts features by applying a scaled dot-product attention mechanism to the embedding vectors of the head entity and relationship, generating a joint feature vector, and then scores the triplet by performing an inner product operation with the tail entity, thereby achieving knowledge graph completion. To verify the effectiveness of the AttenE model, we conducted experimental evaluations on two standard datasets, FB15K-237 and WN18RR and compared its performance with existing classic models across four metrics: MRR, Hit@10, Hit@3 and Hit@1. The experimental results demonstrate that the AttenE model achieves significant performance improvements across multiple metrics, indicating that it can effectively capture high-order interaction information between entities and relationships.
Förderung
- the Science and Technology Project of China Southern Power Grid Co. Ltd.
- the Special Fund for the Central Government to Guide Local Science
- the Key Research and Development Program of Yunnan Province
- the National Natural Science Foundation of China
- the open project of the Key Laboratory of Media Convergence in Yunnan Province
Zitieren
APA
Mou, X., Chen, J., Wang, B., Wang, W., Luo, C., Li, Z., Zhu, Y., Yang, S., Hu, J., & Zhao, N. (2026). AttenE: A knowledge graph completion model based on entity-relation attention embedding. International Journal of Modern Physics C, 37(06). https://doi.org/10.1142/s0129183125420185
Vancouver
Mou X, Chen J, Wang B, Wang W, Luo C, Li Z, et al. AttenE: A knowledge graph completion model based on entity-relation attention embedding. International Journal of Modern Physics C. 2026;37(06). doi:10.1142/s0129183125420185
BibTeX
@article{Mou2026,
author = {Mou, Xuepeng and Chen, Julong and Wang, Bin and Wang, Wei and Luo, Chen and Li, Zhen and Zhu, Yongqing and Yang, Shiping and Hu, Jianhong and Zhao, Na},
title = {AttenE: A knowledge graph completion model based on entity-relation attention embedding},
journal = {International Journal of Modern Physics C},
year = {2026},
volume = {37},
number = {06},
doi = {10.1142/s0129183125420185}
}
EUVIMED