基于多视图融合与多特征提取的知识图谱补全方法  

Knowledge Graph Completion Based on Multi-View Fusion and Multi-Feature Extraction

作　　者：谢珺[1] 杨海洋 续欣莹 程兰 张亚睿 吕佳琪 Xie Jun;Yang Haiyang;Xu Xinying;Cheng Lan;Zhang Yarui;LüJiaqi(School of Electronic Information and Optical Engineering,Taiyuan University of Technology,Jinzhong 030600,China;College of Electrical and Power Engineering,Taiyuan University of Technology,Taiyuan 030024,China)

机构地区：[1]太原理工大学电子信息与光学工程学院,晋中030600 [2]太原理工大学电气与动力工程学院,太原030024

出　　处：《数据分析与知识发现》2025年第1期79-89,共11页Data Analysis and Knowledge Discovery

基　　金：国家自然科学基金项目(项目编号:62073232);山西省科技合作交流专项基金项目(项目编号:202104041101030);山西省自然科学基金项目(项目编号:202103021224056)的研究成果之一。

摘　　要：【目的】针对现有知识图谱补全模型知识表示质量低、模型性能差等问题,提出一种基于多视图融合与多特征提取的知识图谱补全方法。【方法】通过视图编码器生成多个单视图网络,利用注意力机制融合不同视图信息作为实体的最终知识表示;通过不同的特征提取器分别提取头实体与关系的语义和交互特征,利用交叉注意力模块融合语义和交互特征并与尾实体进行匹配。【结果】在链接预测任务中的实验结果表明,与基线模型相比,本文模型在通用数据集FB15K-237和WN18RR上的Hits@10指标分别提升0.4和0.7个百分点,在领域数据集Kinship和UMLS上的Hits@10指标分别达到99.0%和99.9%。【局限】在视图更新时未更新关系,关系知识表示向量质量一般。【结论】多视图融合模型能够有效提升知识图谱表示质量,多特征提取框架能够有效提升链接预测精度。[Objective]This article proposes a knowledge graph completion method based on multi-view fusion and multi-feature extraction,aiming to address issues of low-quality knowledge representation and poor performance in existing models.[Methods]Firstly,we generated multiple single-view networks through a view encoder and obtained the final knowledge representation of the entity using multi-view attention to fuse information from different views.Secondly,we extracted semantic and interaction features of the head entity and the relations with different feature extractors.Finally,we employed a cross-attention module to fuse the semantic and interaction features and match them with tail entities.[Results]Experiments on the link prediction task showed that compared to baseline models,the proposed model improved the Hits@10 metric by 0.4%and 0.9%on the general datasets FB15K-237 and WN18RR,respectively.The Hits@10 metric on the domain datasets Kinship and UMLS reached 99.0%and 99.9%.[Limitations]Relationship was not updated during view updates,resulting in an average quality of relation knowledge representation vectors.[Conclusions]The multi-view fusion model effectively improves the quality of knowledge graph representation,and the multi-feature extraction framework significantly enhances link prediction accuracy.

关 键 词：知识图谱补全 多视图注意力机制 交互特征 语义特征 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]