基于实体与关系融合的知识图谱补全模型研究  

Knowledge Graph Completion Model Based on Entity and Relation Fusion

作　　者：张贞港 余传明[1] Zhang Zhengang;Yu Chuanming(School of Information and Safety Engineering,Zhongnan University of Economics and Law,Wuhan 430073,China)

机构地区：[1]中南财经政法大学信息与安全工程学院,武汉430073

出　　处：《数据分析与知识发现》2023年第2期15-25,共11页Data Analysis and Knowledge Discovery

基　　金：国家自然科学基金面上项目(项目编号:71974202);中南财经政法大学中央高校基本科研业务费专项资金资助项目(项目编号:202311401)的研究成果之一。

摘　　要：【目的】将实体与关系融合,通过加权图卷积神经网络和关系归纳机制,聚合知识图谱的全局信息,增强知识图谱表示质量,提升其在知识图谱补全任务的效果。【方法】提出一种新的用于知识图谱补全任务的端到端学习模型,该模型由邻居信息聚合模块、实体关系融合模块、交互模块和预测模块组成。邻居信息聚合模块聚合实体的邻居信息以丰富实体表示;实体关系融合模块利用实体之间的关系融合实体表示与关系表示;交互模块通过构建核心张量增强与实体和关系表示的交互;预测模块获取最终的预测结果。将所提模型应用到FB15K237、WN18RR、Kinship和UMLS4个数据集上,开展实证研究。【结果】与传统的知识图谱补全模型相比,所提模型的Hits@1指标在FB15K237、WN18RR、Kinship和UMLS这4个数据集上分别提升4.1、3.9、17.8和5.3个百分点。【局限】尚未探究知识图谱补全模型迁移到信息检索、推荐系统等任务上的效果。【结论】通过加权图卷积网络,关系归纳机制以及对比学习损失能够显著提升知识图谱补全任务的效果。本研究对于补全知识图谱中的缺失信息,提升知识图谱在信息检索、自动问答等领域的应用效果具有重要参考意义。[Objective] This study aggregates the global information of knowledge graph through a weighted graph convolutional neural network and a relational induction mechanism, aiming to enhance the quality of the knowledge graph representation and completion. [Methods] We proposed an end-to-end learning model for the knowledge graph completion task, which included a neighborhood information aggregation module, an entity relationship fusion module, an interaction module, as well as a prediction module. This new model aggregates the neighborhood information of entities to enrich their representations. It also enhances the interaction between entities and relationship representations with a core tensor. [Results] We examined the new model with the FB15K237, WN18RR, Kinship, and UMLS datasets. Compared with traditional knowledge graph completion models, the Hits@1 indicators of the proposed model increased by 4.1%, 3.9%, 17.8%, and 5.3% on the four datasets, respectively. [Limitations] We did not explore the performance of our new model on information retrieval and recommendation systems. [Conclusions] The proposed model significantly improves the effectiveness of the knowledge graph completion, which helps us identify missing information in knowledge graphs and may benefit information retrieval and automatic Q&A applications.

关 键 词：知识图谱 知识图谱补全 深度学习 图卷积网络 

分 类 号：G353[文化科学—情报学]