Editorial
Leveraging Relation Attention Mechanisms for Enhanced Knowledge Graph Completion with Embedding Translation
@ARTICLE{10.4108/eetsis.9117, author={Jiahao Shi and Zhengping Lin and Yuzhong Zhou and Yuliang Yang and Jie Lin}, title={Leveraging Relation Attention Mechanisms for Enhanced Knowledge Graph Completion with Embedding Translation}, journal={EAI Endorsed Transactions on Scalable Information Systems}, volume={12}, number={4}, publisher={EAI}, journal_a={SIS}, year={2025}, month={10}, keywords={Knowledge graph, relation attention mechanism, embedding translation, performance evaluation}, doi={10.4108/eetsis.9117} }- Jiahao Shi
Zhengping Lin
Yuzhong Zhou
Yuliang Yang
Jie Lin
Year: 2025
Leveraging Relation Attention Mechanisms for Enhanced Knowledge Graph Completion with Embedding Translation
SIS
EAI
DOI: 10.4108/eetsis.9117
Abstract
In this paper, we propose a novel knowledge graph completion framework to leverage a relation-specific attention mechanism integrated with an embedding translation strategy to improve the accuracy and contextual understanding of link prediction tasks. Unlike traditional models that rely on fixed transformation spaces, the proposed method dynamically captures fine-grained relational semantics by combining hierarchical candidate categorization, relation-guided entity projection, and asymmetric score functions. Specifically, the proposed model employs K-means clustering and principal component analysis (PCA) to identify semantically consistent entity sets, and integrates attention-weighted multi-attribute embeddings to construct robust relational representations. A margin-based ranking loss with normalized embedding constraints ensures effective optimization, further supported by Xavier initialization and stochastic gradient descent. Extensive experiments on two benchmark datasets, WN18 and FB15K, demonstrate the superiority of the proposed method. Specifically, on WN18, the proposed method achieves the lowest mean rank (MR) of 144, with competitive results in mean reciprocal rank (MRR) (0.902), Hits@1 (89.0%), Hits@3 (90.4%), and Hits@10 (96.3%), closely rivaling state- of-the-art models like QuatE and ComplEx. On FB15K, the proposed method again delivers the best Mean Rank of 21, along with strong scores in MRR (0.831), Hits@1 (72.2%), Hits@3 (88.4%), and the highest Hits@10 (92.5%) among all compared methods.
Copyright © 2025 Zhengping Lin et al., licensed to EAI. This is an open access article distributed under the terms of the Creative Commons Attribution license, which permits unlimited use, distribution and reproduction in any medium so long as the original work is properly cited.
