Journal Home > Volume 29 , Issue 5
Tsinghua Science and Technology 2024, 29(5): 1554-1565 https://doi.org/10.26599/TST.2023.9010142
Open Access | Issue | Published: 02 May 2024

A Temporal Knowledge Graph Embedding Model Based on Variable Translation

Show Author's Information Yadan Han1,  Guangquan Lu1( ),  Shichao Zhang1,  Liang Zhang1,  Cuifang Zou1,  Guoqiu Wen1
Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin 541004, China and also with Guangxi Key Lab of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin 541004, China
Keywords:
knowledge graph, link prediction, knowledge graph completion, variable translation, temporal properties, triplet classification
Cite this article:
Han Y, Lu G, Zhang S, et al. A Temporal Knowledge Graph Embedding Model Based on Variable Translation. Tsinghua Science and Technology, 2024, 29(5): 1554-1565. https://doi.org/10.26599/TST.2023.9010142
Download citation
EndNote(RIS)
BibTeX

78

Views

11

Downloads

Citations

0

Crossref

0

WoS

0

Scopus

0

CSCD

Abstract Full text About this article

Knowledge representation learning (KRL) aims to encode entities and relationships in various knowledge graphs into low-dimensional continuous vectors. It is popularly used in knowledge graph completion (or link prediction) tasks. Translation-based knowledge representation learning methods perform well in knowledge graph completion (KGC). However, the translation principles adopted by these methods are too strict and cannot model complex entities and relationships (i.e., N-1, 1-N, and N-N) well. Besides, these traditional translation principles are primarily used in static knowledge graphs and overlook the temporal properties of triplet facts. Therefore, we propose a temporal knowledge graph embedding model based on variable translation (TKGE-VT). The model proposes a new variable translation principle, which enables flexible transformation between entities and relationship embedding. Meanwhile, this paper considers the temporal properties of both entities and relationships and applies the proposed principle of variable translation to temporal knowledge graphs. We conduct link prediction and triplet classification experiments on four benchmark datasets: WN11, WN18, FB13, and FB15K. Our model outperforms baseline models on multiple evaluation metrics according to the experimental results.


menu
Abstract
Full text
Outline
About this article

A Temporal Knowledge Graph Embedding Model Based on Variable Translation

Show Author's information Yadan Han1, Guangquan Lu1( ), Shichao Zhang1, Liang Zhang1, Cuifang Zou1, Guoqiu Wen1
Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin 541004, China and also with Guangxi Key Lab of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin 541004, China

Abstract

Knowledge representation learning (KRL) aims to encode entities and relationships in various knowledge graphs into low-dimensional continuous vectors. It is popularly used in knowledge graph completion (or link prediction) tasks. Translation-based knowledge representation learning methods perform well in knowledge graph completion (KGC). However, the translation principles adopted by these methods are too strict and cannot model complex entities and relationships (i.e., N-1, 1-N, and N-N) well. Besides, these traditional translation principles are primarily used in static knowledge graphs and overlook the temporal properties of triplet facts. Therefore, we propose a temporal knowledge graph embedding model based on variable translation (TKGE-VT). The model proposes a new variable translation principle, which enables flexible transformation between entities and relationship embedding. Meanwhile, this paper considers the temporal properties of both entities and relationships and applies the proposed principle of variable translation to temporal knowledge graphs. We conduct link prediction and triplet classification experiments on four benchmark datasets: WN11, WN18, FB13, and FB15K. Our model outperforms baseline models on multiple evaluation metrics according to the experimental results.

Keywords: knowledge graph, link prediction, knowledge graph completion, variable translation, temporal properties, triplet classification

References(41)

[1]
K. Bollacker, C. Evans, P. Paritosh, T. Sturge, and J. Taylor, Freebase: A collaboratively created graph database for structuring human knowledge, in Proc. 2008 ACM SIGMOD Int. Conf. Management of data, Vancouver, Canada, 2008, pp. 1247–1250.
DOI
[2]

G. Miller, WordNet: A lexical database for English, CACM, vol. 38, no. 11, pp. 39–41, 1995.
DOI Google Scholar
[3]
F. M. Suchanek, G. Kasneci, and G. Weikum, Yago: A core of semantic knowledge, in Proc. 16th Int. Conf. World Wide Web, Banff, Canada, 2007, pp. 697–706.
DOI
[4]

T. Mitchell, W. Cohen, E. Hruschka, P. Talukdar, B. Yang, J. Betteridge, A. Carlson, B. Dalvi, M. Gardner, B. Kisiel, et al., Never-ending learning, CACM, vol. 61, no. 5, pp. 103–115, 2018.
DOI Google Scholar
[5]

G. Q. Lu, J. C. Li, and J. Wei, Aspect sentiment analysis with heterogeneous graph neural networks, Information Processing & Management, vol. 59, no. 4, p. 10, 2953.
Google Scholar
[6]

G. Lu and J. Huang, Learning representation from concurrence-words graph for aspect sentiment classification, Comput J, vol. 64, no. 7, pp. 1069–1079, 2021.
DOI Google Scholar
[7]

F. Huang, X. Li, C. Yuan, S. Zhang, J. Zhang, and S. Qiao, Attention-emotion-enhanced convolutional LSTM for sentiment analysis, IEEE Trans. Neural Netw. Learning Syst., vol. 33, no. 9, pp. 4332–4345, 2022.
DOI Google Scholar
[8]

J. Li, G. Lu, Z. Wu, and F. Ling, Multi-view representation model based on graph autoencoder, Inf. Sci., vol. 632, pp. 439–453, 2023.
DOI Google Scholar
[9]
J. Gan, R. Hu, Y. Mo, Z. Kang, L. Peng, Y. Zhu, and X. Zhu, Multigraph fusion for dynamic graph convolutional network, IEEE Trans. Neural Netw. Learning Syst., pp. 1–12, 2022.
[10]
L. Peng, Y. Mo, J. Xu, J. Shen, X. Shi, X. Li, H. T. Shen, and X. Zhu, GRLC: graph representation learning with constraints, IEEE Trans. Neural Netw. Learning Syst., pp. 1–14, 2023.
DOI
[11]

Y. Mo, Y. Chen, Y. Lei, L. Peng, X. Shi, C. Yuan, and X. Zhu, Multiplex graph representation learning via dual correlation reduction, IEEE Trans. Knowl. Data Eng., vol. 35, no. 12, pp. 12814–12827, 2023.
DOI Google Scholar
[12]

G. Lu, J. Gan, J. Yin, Z. Luo, B. Li, and X. Zhao, Multi-task learning using a hybrid representation for text classification, Neural Comput. Appl., vol. 32, no. 11, pp. 6467–6480, 2020.
DOI Google Scholar
[13]
Y. H. Zhu, J. B. Ma, C. A. Yuan, and X. F. Zhu, Interpretable learning based Dynamic Graph Convolutional Networks for Alzheimer’s Disease analysis, Information Fusion, vol. 77, 2022, pp. 53–61.
DOI
[14]
R. West, E. Gabrilovich, K. Murphy, S. Sun, R. Gupta, and D. Lin, Knowledge base completion via search-based question answering, in Proc. 23rd Int. Conf. World wide web, Seoul, Republic of Korea, 2014, pp. 515–526.
DOI
[15]

A. Bordes, N. Usunier, A. Garcia-Durán, J. Weston, and O. Yakhnenko, Translating embeddings for modeling multi-relational data, Adv. Neural Inf. Process. Syst., vol. 2, pp. 2787–2795, 2013.
Google Scholar
[16]
Z. Wang, J. Zhang, J. Feng, and Z. Chen, Knowledge graph embedding by translating on hyperplanes, in Proc. Twenty-Eighth AAAI Conf. Artif. Intell., Québec City, Canada, 2014, pp. 1112–1119.
DOI
[17]
J. Feng, M. Huang, M. Wang, M. Zhou, Y. Hao, and X. Zhu, Knowledge graph embedding by flexible translation, in Proc. Fifteenth Int. Conf. Principles of Knowledge Representation and Reasoning, Cape Town, South Africa, 2016, pp. 557–560.
[18]

L. Chang, M. Zhu, T. Gu, C. Bin, J. Qian, and J. Zhang, Knowledge graph embedding by dynamic translation, IEEE Access, vol. 5, pp. 20898–20907, 2017.
DOI Google Scholar
[19]
Y. Lin, Z. Liu, M. Sun, Y. Liu, and X. Zhu, Learning entity and relation embeddings for knowledge graph completion, in Proc. 29th AAAI Conf. Artif. Intell., Austin, TX, USA, 2015, pp. 2181–2187.
DOI
[20]
G. Ji, S. He, L. Xu, K. Liu, and J. Zhao, Knowledge graph embedding via dynamic mapping matrix, in Proc. 53rd Annual Meeting of the Association for Computational Linguistics and the 7th Int. Joint Conf. Natural Language Processing (Volume 1 : Long Papers), Beijing, China, 2015, pp. 687–696.
DOI
[21]
Y. Li, W. Fan, C. Liu, C. Lin, and J. Qian, TranSHER: Translating knowledge graph embedding with hyper-ellipsoidal restriction, in Proc. 2022 Conf. Empirical Methods in Natural Language Processing, Abu Dhabi, United Arab Emirates, 2022, pp. 8517−8528.
DOI
[22]

Y. Ma, G. Altenbek, and X. Wu, Knowledge graph embedding via entity and relationship attributes, Multimed. Tools Appl., vol. 82, no. 28, pp. 44071–44086, 2023.
DOI Google Scholar
[23]
T. Jiang, T. Liu, T. Ge, L. Sha, S. Li, B. Chang, and Z. Sui, Encoding temporal information for time-aware link prediction, in Proc. 2016 Conf. Empirical Methods in Natural Language Processing, Austin, TX, USA, 2016, pp. 2350–2354.
DOI
[24]

J. Messner, R. Abboud, and I. I. Ceylan, Temporal knowledge graph completion using box embeddings, Proc. AAAI Conf. Artif. Intell., vol. 36, no. 7, pp. 7779–7787, 2022.
DOI Google Scholar
[25]
R. Abboud, İ. İ. Ceylan, T. Lukasiewicz, and T. Salvatori, BoxE: A box embedding model for knowledge base completion, arXiv preprint arXiv: 2007.06267, 2020.
[26]

P. Shao, D. Zhang, G. Yang, J. Tao, F. Che, and T. Liu, Tucker decomposition-based temporal knowledge graph completion, Knowl. Based Syst., vol. 238, p. 107841, 2022.
DOI Google Scholar
[27]
N. Park, F. Liu, P. Mehta, D. Cristofor, C. Faloutsos, and Y. Dong, EvoKG: Jointly modeling event time and network structure for reasoning over temporal knowledge graphs, in Proc. Fifteenth ACM Int. Conf. Web Search and Data Mining, Virtual Event, 2022, pp. 794–803.
DOI
[28]
F. Zhang, Z. Zhang, X. Ao, F. Zhuang, Y. Xu, and Q. He, Along the time: Timeline-traced embedding for temporal knowledge graph completion, in Proc. 31st ACM Int. Conf. Information & Knowledge Management, Atlanta, GA, USA, 2022, pp. 2529–2538.
DOI
[29]

R. Goel, S. M. Kazemi, M. Brubaker, and P. Poupart, Diachronic embedding for temporal knowledge graph completion, Proc. AAAI Conf. Artif. Intell., vol. 34, no. 4, pp. 3988–3995, 2020.
DOI Google Scholar
[30]
X. Hou, R. Ma, L. Yan, and Z. Ma, T-GAE: A timespan-aware graph attention-based embedding model for temporal knowledge graph completion, Inf. Sci., vol. 642, p. 119225, 2023.
DOI
[31]
B. An, X. Han, L. Sun, and J. Wu, Triple classification based on synthesized features for knowledge base, https://www.semanticscholar.org/paper/Triple-Classification-Based-on-Synthesized-Features-Bo-Xianpei/190496c1f145bf8e66aeb7e1d0c9acfd48cc33b4, 2016.
[32]
B. S. Yang, W. T. Yih, X. D. He, J. F. Gao, and L. Deng, Embedding entities and relations for learning and inference in knowledge bases, in 3rd Int. Conf. Learning Representations, San Diego, CA, USA, 2015.
[33]
G. Ji, K. Liu, S. He, and J. Zhao, Knowledge graph completion with adaptive sparse transfer matrix, in Proc. 30th AAAI Conf. Artif. Intell., Phoenix, AZ, USA, 2016, pp. 985–991.
DOI
[34]
D. Q. Nguyen, K. Sirts, L. Qu, and M. Johnson, STransE: A novel embedding model of entities and relationships in knowledge bases, arXiv preprint arXiv: 1606.08140, 2016.
DOI
[35]
X. Zhou, Q. Zhu, P. Liu, and L. Guo, Learning knowledge embeddings by combining limit-based scoring loss, in Proc. 2017 ACM on Conf. Information and Knowledge Management, Singapore, 2017, pp. 1009–1018.
DOI
[36]
W. Qian, C. Fu, Y. Zhu, D. Cai, and X. He, Translating embeddings for knowledge graph completion with relation attention mechanism, in IJCAI'18 : Proc. 27th Int. Joint Conf. on Artif. Intell., Stockholm, Sweden, pp. 4286–4292, 2018.
DOI
[37]
Y. Zhu, H. Liu, Z. Wu, Y. Song, and T. Zhang, Representation learning with ordered relation paths for knowledge graph completion, in Proc. 2019 Conf. Empirical Methods in Natural Language Processing and the 9th Int. Joint Conf. Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China, 2019, pp. 2662–2671.
DOI
[38]

G. Niu, Y. Zhang, B. Li, P. Cui, S. Liu, J. Li, and X. Zhang, Rule-guided compositional representation learning on knowledge graphs, Proc. AAAI Conf. Artif. Intell., vol. 34, no. 3, pp. 2950–2958, 2020.
DOI Google Scholar
[39]
L. Lin, J. Liu, F. Guo, C. Tong, L. Zu, and H. Guo, ERDERP: Entity and relation double embedding on relation hyperplanes and relation projection hyperplanes, Mathematics, vol. 10, no. 22, p. 4182, 2022.
DOI
[40]

W. Chen, S. Zhao, and X. Zhang, Enhancing knowledge graph embedding with type-constraint features, Appl. Intell., vol. 53, no. 1, pp. 984–995, 2023.
DOI Google Scholar
[41]
S. Yang, J. Tian, H. Zhang, J. Yan, H. He, and Y. Jin, TransMS: knowledge graph embedding for complex relations by multidirectional semantics, pp. 1935−1942, 2019.
DOI
Publication history
Copyright
Acknowledgements
Rights and permissions

Publication history

Received: 20 June 2023
Revised: 13 October 2023
Accepted: 21 November 2023
Published: 02 May 2024
Issue date: October 2024

Copyright

© The Author(s) 2024.

Acknowledgements

Acknowledgment

The work was supported partly by National Natural Science Foundation of China (Nos. 62372119 and 62166003), the Project of Guangxi Science and Technology (Nos. GuiKeAB23026040 and GuiKeAD20159041), the Innovation Project of Guangxi Graduate Education (No. YCSW2023188), Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, China, Intelligent Processing and the Research Fund of Guangxi Key Lab of Multi-source Information Mining & Security (Nos. 20-A-01-01 and MIMS21-M-01), Open Research Fund of Guangxi Key Lab of Human-machine Interaction and Intelligent Decision (No. GXHIID2206), the Guangxi Collaborative Innovation Center of Multi-Source Information Integration and the Guangxi “Bagui” Teams for Innovation and Research, China.

Rights and permissions

The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).

Return