Temporal Knowledge Graph Reasoning Based on Entity Relationship Similarity Perception

被引:1
|
作者
Feng, Siling [1 ]
Zhou, Cong [1 ]
Liu, Qian [1 ]
Ji, Xunyang [1 ]
Huang, Mengxing [1 ]
机构
[1] Hainan Univ, Sch Informat & Commun Engn, Haikou 570228, Peoples R China
基金
中国国家自然科学基金;
关键词
temporal knowledge graph; similarity measurement method; similarity features;
D O I
10.3390/electronics13122417
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Temporal knowledge graphs (TKGs) are used for dynamically modeling facts in the temporal dimension, and are widely used in various fields. However, existing reasoning models often fail to consider the similarity features between entity relationships and static attributes, making it difficult for them to effectively handle these temporal attributes. Therefore, these models have limitations in dealing with previously invisible entities that appear over time and the implicit associations of static attributes between entities. To address this issue, we propose a temporal knowledge graph reasoning model based on Entity Relationship Similarity Perception, known as ERSP. This model employs the similarity measurement method to capture the similarity features of entity relationships and static attributes, and then fuses these features to generate structural representations. Finally, we provide a decoder with entity relationship representation, static attribute representation, and structural representation information to form a quadruple. Experiments conducted on five common benchmark datasets show that ERSP surpasses the majority of TKG reasoning methods.
引用
收藏
页数:20
相关论文
共 50 条
  • [41] Research Progress and Trend of Temporal Knowledge Graph Representation and Reasoning
    Wang, Yu-Han
    Chen, Zi-Yang
    Zhao, Xiang
    Tan, Zhen
    Xiao, Wei-Dong
    Cheng, Xue-Qi
    Ruan Jian Xue Bao/Journal of Software, 2024, 35 (08): : 3923 - 3951
  • [42] Reinforcement learning with time intervals for temporal knowledge graph reasoning
    Liu, Ruinan
    Yin, Guisheng
    Liu, Zechao
    Tian, Ye
    INFORMATION SYSTEMS, 2024, 120
  • [43] Temporal knowledge graph question answering via subgraph reasoning
    Chen, Ziyang
    Zhao, Xiang
    Liao, Jinzhi
    Li, Xinyi
    Kanoulas, Evangelos
    KNOWLEDGE-BASED SYSTEMS, 2022, 251
  • [44] Complex Evolutional Pattern Learning for Temporal Knowledge Graph Reasoning
    Li, Zixuan
    Guan, Saiping
    Jin, Xiaolong
    Peng, Weihua
    Lyu, Yajuan
    Zhu, Yong
    Bai, Long
    Li, Wei
    Guo, Jiafeng
    Cheng, Xueqi
    PROCEEDINGS OF THE 60TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022): (SHORT PAPERS), VOL 2, 2022, : 290 - 296
  • [45] Intricate Spatiotemporal Dependency Learning for Temporal Knowledge Graph Reasoning
    Li, Xuefei
    Zhou, Huiwei
    Yao, Weihong
    Li, Wenchu
    Liu, Baojie
    Lin, Yingyu
    ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA, 2024, 18 (06)
  • [46] DegreEmbed: Incorporating entity embedding into logic rule learning for knowledge graph reasoning
    Li, Haotian
    Liu, Hongri
    Wang, Yao
    Xin, Guodong
    Wei, Yuliang
    SEMANTIC WEB, 2023, 14 (06) : 1099 - 1119
  • [47] Analysis of Knowledge Graph Path Reasoning Based on Variational Reasoning
    Tang, Hongmei
    Tang, Wenzhong
    Li, Ruichen
    Wang, Yanyang
    Wang, Shuai
    Wang, Lihong
    APPLIED SCIENCES-BASEL, 2022, 12 (12):
  • [48] An entity-graph based reasoning method for fact verification
    Chen, Chonghao
    Cai, Fei
    Hu, Xuejun
    Zheng, Jianming
    Ling, Yanxiang
    Chen, Honghui
    INFORMATION PROCESSING & MANAGEMENT, 2021, 58 (03)
  • [49] GRAPH-BASED KNOWLEDGE REPRESENTATION AND REASONING
    Chein, M.
    ICEIS 2010: PROCEEDINGS OF THE 12TH INTERNATIONAL CONFERENCE ON ENTERPRISE INFORMATION SYSTEMS, VOL 1: DATABASES AND INFORMATION SYSTEMS INTEGRATION, 2010, : IS17 - IS21
  • [50] Flow to Candidate: Temporal Knowledge Graph Reasoning With Candidate-Oriented Relational Graph
    Fan, Shiqi
    Fan, Guoxi
    Nie, Hongyi
    Yao, Quanming
    Liu, Yang
    Li, Xuelong
    Wang, Zhen
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024,