Journal of Frontiers of Computer Science and Technology ›› 2022, Vol. 16 ›› Issue (8): 1800-1808.DOI: 10.3778/j.issn.1673-9418.2104084

• Artificial Intelligence • Previous Articles     Next Articles

Knowledge Graph Link Prediction Based on Subgraph Reasoning

YU Huilin, CHEN Wei, WANG Qi, GAO Jianwei, WAN Huaiyu   

  1. School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, China
  • Received:2021-03-26 Revised:2021-05-31 Online:2022-08-01 Published:2021-06-03
  • About author:YU Huilin, born in 1997, M.S. candidate. Her research interests include knowledge graph reasoning and information extraction.
    CHEN Wei, born in 1994, Ph.D. candidate. His research interests include knowledge graph reasoning and application.
    GAO Jianwei, born in 1995, M.S. candidate. His research interests include knowledge graph and information extraction.
    WAN Huaiyu, born in 1981, Ph.D., associate professor, member of CCF. His research interests include social network mining, text information extraction, user behavior analysis and spatial-temporal data mining.
  • Supported by:
    the National Key Research and Development Program of China(2018YFC0830200)


于慧琳, 陈炜, 王琪, 高建伟, 万怀宇   

  1. 北京交通大学 计算机与信息技术学院,北京 100044
  • 作者简介:于慧琳(1997—),女,黑龙江佳木斯人,硕士研究生,主要研究方向为知识图谱推理、信息抽取。
  • 基金资助:


Relationship prediction in knowledge graph aims to identify and infer new relationships from existing data, and provides knowledge services for many downstream tasks. At present, many researches solve the link prediction problem between entities by mapping entities and relations into a vector space or searching the paths between entities. These methods only consider the influence of single path or first-order information but ignore more complex relation information between entities. Therefore, this paper proposes a novel link prediction method based on subgraph reasoning in knowledge graph, uses the subgraph structure to obtain the entity pair neighborhood structure information, combines the advantages of representation learning and path reasoning, and realizes the relationship prediction between entities. This paper first extends the paths between entities to subgraphs, constructs node subgraph and relationship subgraph from entity level and relationship level respectively, then combines the graph embedding representation with the graph neural network to calculate the subgraph features, to get richer entity characteristics and relationship characteristics. Finally, this paper calculates the neighborhood structure information of entity pairs from the subgraph structure to conduct link prediction between entities. Experimental results demons-trate that the proposed approach outperforms other reasoning-based link prediction methods on two benchmark datasets.

Key words: knowledge graph, link prediction, subgraph construction, graph neural network



关键词: 知识图谱, 连接预测, 子图构建, 图神经网络

CLC Number: