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
  • [21] A Novel Encoder-Decoder Knowledge Graph Completion Model for Robot Brain
    Song, Yichen
    Li, Aiping
    Tu, Hongkui
    Chen, Kai
    Li, Chenchen
    [J]. FRONTIERS IN NEUROROBOTICS, 2021, 15
  • [22] Logic and Commonsense-Guided Temporal Knowledge Graph Completion
    Niu, Guanglin
    Li, Bo
    [J]. THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 4, 2023, : 4569 - 4577
  • [23] MADE: Multicurvature Adaptive Embedding for Temporal Knowledge Graph Completion
    Wang, Jiapu
    Wang, Boyue
    Gao, Junbin
    Pan, Shirui
    Liu, Tengfei
    Yin, Baocai
    Gao, Wen
    [J]. IEEE TRANSACTIONS ON CYBERNETICS, 2024, : 5818 - 5831
  • [24] Tensor decompositions for temporal knowledge graph completion with time perspective
    Yang, Jinfa
    Ying, Xianghua
    Shi, Yongjie
    Xing, Bowei
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2024, 237
  • [25] Geometry Interaction Embeddings for Interpolation Temporal Knowledge Graph Completion
    Zhao, Xuechen
    Miao, Jinfeng
    Yang, Fuqiang
    Pang, Shengnan
    [J]. MATHEMATICS, 2024, 12 (13)
  • [26] Time in a Box: Advancing Knowledge Graph Completion with Temporal Scopes
    Cai, Ling
    Janowicz, Krzysztof
    Yan, Bo
    Zhu, Rui
    Mai, Gengchen
    [J]. PROCEEDINGS OF THE 11TH KNOWLEDGE CAPTURE CONFERENCE (K-CAP '21), 2021, : 121 - 128
  • [27] SANe: Space adaptation network for temporal knowledge graph completion
    Li, Yancong
    Zhang, Xiaoming
    Zhang, Bo
    Huang, Feiran
    Chen, Xiaopeng
    Lu, Ming
    Ma, Shuai
    [J]. INFORMATION SCIENCES, 2024, 667
  • [28] QDN: A Quadruplet Distributor Network for Temporal Knowledge Graph Completion
    Wang, Jiapu
    Wang, Boyue
    Gao, Junbin
    Li, Xiaoyan
    Hu, Yongli
    Yin, Baocai
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2023, 35 (10) : 1 - 13
  • [29] Tucker decomposition-based temporal knowledge graph completion
    Shao, Pengpeng
    Zhang, Dawei
    Yang, Guohua
    Tao, Jianhua
    Che, Feihu
    Liu, Tong
    [J]. KNOWLEDGE-BASED SYSTEMS, 2022, 238
  • [30] Knowledge Graph Completion: A Review
    Chen, Zhe
    Wang, Yuehan
    Zhao, Bin
    Cheng, Jing
    Zhao, Xin
    Duan, Zongtao
    [J]. IEEE ACCESS, 2020, 8 (08): : 192435 - 192456