知识图谱嵌入研究进展综述  

Review of Research Progress on Knowledge Graph Embedding

作　　者：马恒志 钱育蓉[1,2,3] 冷洪勇 吴海鹏[2,3] 陶文彬 张依杨 MA Hengzhi;QIAN Yurong;LENG Hongyong;WU Haipeng;TAO Wenbin;ZHANG Yiyang(College of Software,Xinjiang University,Urumqi 830046 Xinjiang,China;Key Laboratory of Signal Detection and Processing of Xinjiang Uygur Autonomous Region,Urumqi 830046,Xinjiang,China;College of Information Science and Engineering,Xinjiang University,Urumqi 830046,Xinjiang,China)

机构地区：[1]新疆大学软件学院,新疆乌鲁木齐830046 [2]新疆维吾尔自治区信号检测与处理重点实验室,新疆乌鲁木齐830046 [3]新疆大学信息科学与工程学院,新疆乌鲁木齐830046

出　　处：《计算机工程》2025年第2期18-34,共17页Computer Engineering

基　　金：国家自然科学基金(61966035,62266043)。

摘　　要：随着大数据和人工智能技术的不断发展,知识图谱应用越来越广泛,知识图谱嵌入技术也得到了飞速发展。知识图谱嵌入通过在低维矢量空间中实现结构化知识表示来提高知识表示和推理效率。对知识图谱嵌入技术进行全面概述,包括其基本概念、模型类别、评价指标以及应用前景。首先介绍了知识图谱嵌入的基本概念及背景,将知识图谱嵌入分为基于翻译机制的嵌入模型、基于语义匹配机制的嵌入模型、基于神经网络的嵌入模型和基于附加信息的嵌入模型4个主要类别,并对相关模型的核心思想、评分函数、优缺点、应用场景进行细致梳理;然后总结了知识图谱嵌入的常见数据集和评价指标,以及链接预测和三元组分类等相关应用与实验结果,同时介绍了问答系统、推荐系统等下游任务;最后对知识图谱嵌入技术进行回顾总结,概述了当前知识图谱嵌入技术存在的局限性和主要问题,探讨了未来知识图谱嵌入领域存在的机遇和挑战以及具有潜力的研究方向,并对研究前景进行展望。With the continuous development of big data and artificial intelligence technologies,knowledge graph embedding is developing rapidly,and knowledge graph applications are becoming increasingly widespread.Knowledge graph embedding improves the efficiency of knowledge representation and reasoning by representing structured knowledge into a low-dimensional vector space.This study provides a comprehensive overview of knowledge graph embedding technology,including its basic concepts,model categories,evaluation indices,and application prospects.First,the basic concepts and background of knowledge graph embedding are introduced,classifying the technology into four main categories:embedding models based on translation mechanisms,semantic-matching mechanisms,neural networks,and additional information.The core ideas,scoring functions,advantages and disadvantages,and application scenarios of the related models are meticulously sorted.Second,common datasets and evaluation indices of knowledge graph embedding are summarized,along with application prospects,such as link prediction and triple classification.The experimental results are analyzed,and downstream tasks,such as question-and-answer systems and recommenders,are introduced.Finally,the knowledge graph embedding technology is reviewed and summarized,outlining its limitations and the primary existing problems while discussing the opportunities and challenges for future knowledge graph embedding along with potential research directions.

关 键 词：知识图谱 知识图谱嵌入 知识图谱表示学习 链接预测 三元组分类 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]