A Survey of Temporal Knowledge Graph Reasoning

被引：0
|
作者：
Shen Y.-H. [1 ,2 ]
Jiang X.-H. [1 ,2 ]
Wang Y.-Z. [1 ,3 ]
Li Z.-X. [2 ,4 ]
Li Z.-J. [1 ,2 ]
Tan H.-X. [1 ,2 ]
Shen H.-W. [1 ,2 ]
机构：
[1] Data Intelligence System Research Center, Institute of Computing Technology, Chinese Academy of Sciences, Beijing
[2] University of Chinese Academy of Sciences, Beijing
[3] Zhongke Big Data Academy, Zhengzhou
[4] Key Laboratory of Netvuork Data Science and Technology, Institute of Computing Technology, Chinese Academy of Sciences, Beijing
来源：
Jisuanji Xuebao/Chinese Journal of Computers | 2023年 / 46卷 / 06期
关键词：
knowledge completion; knowledge graph; knowledge prediction; temporal knowledge graph; temporal knowledge reasoning;
D O I：
10.11897/SP.J.1016.2023.01272
中图分类号：
学科分类号：
摘要：
With the rapid development of technologies such as social networks and object-side perception, a large number of interactions, topics, events, news, and other data have emerged in cyberspace, containing a large amount of dynamic evolution and highly time-sensitive knowledge. Compared with traditional knowledge graphs that ignore temporal information in the knowledge, temporal knowledge graphs can describe dynamic features of the real world by modeling the temporal aspect of knowledge and provide effective support for temporal-aware applications. However, the temporal knowledge graph cannot guarantee to cover the total amount of knowledge, and the lack of knowledge seriously affects the application performance. The reasoning model is required to automatically mine new knowledge to explain the historical state of things, predict future development trends and describe the evolution laws. Due to the urgent need for practical applications, in recent years, the research works of temporal knowledge graph reasoning are emerging, attracting increasing attention from academia and industry. This paper comprehensively summarizes existing temporal knowledge graph reasoning studies in recent years. First, the related concepts and problem descriptions of temporal knowledge graph reasoning are introduced. Second, the reasoning models oriented to completion tasks and the reasoning models oriented to prediction tasks are systematically introduced, compared, and analyzed. The datasets, reasoning tasks, related indicators, and application scenarios of temporal knowledge graph reasoning are discussed. Finally, future research trends of temporal knowledge graph reasoning have been prospected. Above all, this paper is dedicated to providing valuable references for researchers in the field of temporal knowledge graphs reasoning for promoting further development in this field. © 2023 Science Press. All rights reserved.
引用
收藏
页码：1272 / 1301
页数：29
相关论文
共 141 条
  • [81] Xu D, Ruan C, Korpeoglu E, Et al., Inductive representation learning on temporal graphs, Proceedings of the 8th International Conference on Learning Representations, (2020)
  • [82] Tian S, Wu R, Shi L, Et al., Self-supervised representation learning on dynamic graphs, Proceedings of the 30th ACM International Conference on Information &: Knowledge Management, pp. 1814-1823, (2021)
  • [83] Zhou Y, Liu W, Pei Y, Et al., Dynamic network embedding by semantic evolution, Proceedings of the 2019 International Joint Conference on Neural Networks (IJCNN), pp. 1-8, (2019)
  • [84] Perozzi B, Al-Rfou R, Skiena S. Skiena S., Deepwalk
  • [85] Online learning of social representations, Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 701-710, (2014)
  • [86] Grover A, Leskovec J., node2vec: Scalable feature learning for networks, Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 855-864, (2016)
  • [87] Mahdavi S, Khoshraftar S, An A., dynnode2vec: Scalable dynamic network embedding, Proceedings of the 2018 IEEE International Conference on Big Data (Big Data), pp. 3762-3765, (2018)
  • [88] Bian R, Koh Y S, Dobbie G, Et al., Network embedding and change modeling in dynamic heterogeneous networks, Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 861-864, (2019)
  • [89] Peng H, Li J, Yan H, Et al., Dynamic network embedding via incremental skip-gram with negative sampling, Science China Information Sciences, 63, 10, pp. 1-19, (2020)
  • [90] Liu Z, Zhou D, Zhu Y, Et al., Towards fine-grained temporal network representation via time-reinforced random walk, Proceedings of the AAAI Conference on Artificial Intelligence, pp. 4973-4980, (2020)
45678910111213