计算机科学与探索 ›› 2023, Vol. 17 ›› Issue (1): 27-52.DOI: 10.3778/j.issn.1673-9418.2207060

• 前沿·综述 • 上一篇    下一篇

图神经网络应用于知识图谱推理的研究综述

孙水发,李小龙,李伟生,雷大江,李思慧,杨柳,吴义熔   

  1. 1. 智慧医疗宜昌市重点实验室,湖北 宜昌 443002
    2. 三峡大学 计算机与信息学院,湖北 宜昌 443002
    3. 三峡大学 经济与管理学院,湖北 宜昌 443002
    4. 重庆邮电大学 计算机科学与技术学院,重庆 400065
    5. 北京师范大学 心理学部,广东 珠海 519087
    6. 北京师范大学 人文和社会科学高等研究院,广东 珠海 519087
  • 出版日期:2023-01-01 发布日期:2023-01-01

Review of Graph Neural Networks Applied to Knowledge Graph Reasoning

SUN Shuifa, LI Xiaolong, LI Weisheng, LEI Dajiang, LI Sihui, YANG Liu, WU Yirong   

  1. 1. Yichang Key Laboratory of Intelligent Medicine,Yichang, Hubei 443002, China
    2. College of Computer and Information Technology, China Three Gorges University, Yichang, Hubei 443002, China
    3. College of Economics and Management, China Three Gorges University, Yichang, Hubei 443002, China
    4. College of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chong-qing 400065, China
    5. Faculty of Psychology, Beijing Normal University, Zhuhai, Guangdong 519087, China
    6. Institute of Advanced Studies in Humanities and Social Sciences, Beijing Normal University, Zhuhai, Guangdong 519087, China
  • Online:2023-01-01 Published:2023-01-01

摘要: 知识推理(KR)作为知识图谱构建的一个重要环节,一直是该领域研究的焦点问题。随着知识图谱应用研究的不断深入和范围的不断扩大,将图神经网络(GNN)应用于知识推理的方法能够在获取知识图谱中实体、关系等语义信息的同时,充分考虑知识图谱的结构信息,使其具备更好的可解释性和更强的推理能力,因此近年来受到广泛关注。首先梳理了知识图谱和知识推理的基本知识及研究现状,简要介绍了基于逻辑规则、基于表示学习、基于神经网络和基于图神经网络的知识推理的优势与不足;其次全面总结了基于图神经网络的知识推理最新进展,将基于图神经网络的知识推理按照基于递归图神经网络(RecGNN)、卷积图神经网络(ConvGNN)、图自编码网络(GAE)和时空图神经网络(STGNN)的知识推理进行分类,对各类典型网络模型进行了介绍和对比分析;然后介绍了基于图神经网络的知识推理在医学、智能制造、军事、交通等领域的应用;最后提出了基于图神经网络的知识推理的未来研究方向,并对这个快速增长领域中的各方向研究进行了展望。

关键词: 知识图谱, 知识推理(KR), 图神经网络(GNN), 语义信息, 结构信息

Abstract: As an important element of knowledge graph construction, knowledge reasoning (KR) has always been a hot topic of research. With the deepening of knowledge graph application research and the expanding of its scope, graph neural network (GNN) based KR methods have received extensive attention due to their capability of obtaining semantic information such as entities and relationships in knowledge graph, high interpretability, and strong reasoning ability. In this paper, firstly, basic knowledge and research status of knowledge graph and KR are summarized. The advantages and disadvantages of KR approaches based on logic rules, representation learning, neural network and graph neural network are briefly introduced. Secondly, the latest progress in KR based on GNN is comprehensively summarized. GNN-based KR methods are categorized into knowledge reasoning based on recurrent graph neural networks (RecGNN), convolutional graph neural networks (ConvGNN), graph auto-encoders (GAE) and spatial-temporal graph neural networks (STGNN). Various typical network models are introduced and compared. Thirdly, this paper introduces the application of KR based on graph neural network in health care, intelligent manufacturing, military, transportation, etc. Finally, the future research directions of GNN-based KR are proposed, and related research in various directions in this rapidly growing field is discussed.

Key words: knowledge graph, knowledge reasoning (KR), graph neural network (GNN), semantic information;structural information