A Simple But Powerful Graph Encoder for Temporal Knowledge Graph Completion

被引:0
|
作者
Ding, Zifeng [1 ,2 ]
Ma, Yunpu [1 ,2 ]
He, Bailan [1 ,2 ]
Wu, Jingpei [3 ]
Han, Zhen [1 ,2 ]
Tresp, Volker [1 ,2 ]
机构
[1] Ludwig Maximilians Univ Munchen, Munich, Germany
[2] Siemens AG, Munich, Germany
[3] Tech Univ Munich, Munich, Germany
关键词
Natural language processing; Representation learning; Temporal knowledge graph;
D O I
10.1007/978-3-031-47715-7_49
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Knowledge graphs contain rich knowledge about various entities and the relational information among them, while temporal knowledge graphs (TKGs) describe and model the interactions of the entities over time. In this context, automatic temporal knowledge graph completion (TKGC) has gained great interest. Recent TKGC methods integrate advanced deep learning techniques, e.g., Transformers, and achieve superior model performance. However, this also introduces a large number of excessive parameters, which brings a heavier burden for parameter optimization. In this paper, we propose a simple but powerful graph encoder for TKGC, called TARGCN. TARGCN is parameter-efficient, and it extensively explores every entity's temporal context for learning contextualized representations. We find that instead of adopting various kinds of complex modules, it is more beneficial to efficiently capture the temporal contexts of entities. We experiment TARGCN on three benchmark datasets. Our model can achieve a more than 46% relative improvement on the GDELT dataset compared with state-of-the-art TKGC models. Meanwhile, it outperforms the strongest baseline on the ICEWS05-15 dataset with around 18% fewer parameters.
引用
收藏
页码:729 / 747
页数:19
相关论文
共 50 条
  • [1] Temporal Knowledge Graph Completion: A Survey
    Cai, Borui
    Xiang, Yong
    Gao, Longxiang
    Zhang, He
    Li, Yunfeng
    Li, Jianxin
    [J]. PROCEEDINGS OF THE THIRTY-SECOND INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2023, 2023, : 6545 - 6553
  • [2] GAEAT: Graph Auto-Encoder Attention Networks for Knowledge Graph Completion
    Han, Yanfei
    Fang, Quan
    Hu, Jun
    Qian, Shengsheng
    Xu, Changsheng
    [J]. CIKM '20: PROCEEDINGS OF THE 29TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT, 2020, : 2053 - 2056
  • [3] Dynamic Embedding Graph Attention Networks for Temporal Knowledge Graph Completion
    Wang, Jingqi
    Zhu, Cui
    Zhu, Wenjun
    [J]. KNOWLEDGE SCIENCE, ENGINEERING AND MANAGEMENT, PT I, 2022, 13368 : 722 - 734
  • [4] Survey on Temporal Knowledge Graph Completion Research
    Xu, Kaijia
    Liu, Lin
    Wang, Hailong
    Liu, Jing
    [J]. Computer Engineering and Applications, 2024, 60 (22) : 38 - 57
  • [5] Diachronic Embedding for Temporal Knowledge Graph Completion
    Goel, Rishab
    Kazemi, Seyed Mehran
    Brubaker, Marcus
    Poupart, Pascal
    [J]. THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 3988 - 3995
  • [6] Sequence Encoder-based Spatiotemporal Knowledge Graph Completion
    Jia, Wei
    Wang, Xuan
    Shan, Jing
    Yan, Li
    Niu, Weinan
    Ma, Zongmin
    [J]. JOURNAL OF WEB ENGINEERING, 2022, 21 (06): : 1913 - 1936
  • [7] TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion
    Wu, Jiapeng
    Cao, Meng
    Cheung, Jackie Chi Kit
    Hamilton, William L.
    [J]. PROCEEDINGS OF THE 2020 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP), 2020, : 5730 - 5746
  • [8] Temporal-structural importance weighted graph convolutional network for temporal knowledge graph completion
    Nie, Haojie
    Zhao, Xiangguo
    Yao, Xin
    Jiang, Qingling
    Bi, Xin
    Ma, Yuliang
    Sun, Yongjiao
    [J]. FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE, 2023, 143 : 30 - 39
  • [9] Leveraging semantic property for temporal knowledge graph completion
    Li, Mingda
    Sun, Zhengya
    Zhang, Wensheng
    Liu, Wei
    [J]. APPLIED INTELLIGENCE, 2023, 53 (08) : 9247 - 9260
  • [10] Leveraging semantic property for temporal knowledge graph completion
    Mingda Li
    Zhengya Sun
    Wensheng Zhang
    Wei Liu
    [J]. Applied Intelligence, 2023, 53 : 9247 - 9260