Skip to main content

Advertisement

Springer Nature Link
Log in

Leveraging semantic property for temporal knowledge graph completion

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Temporal knowledge graphs (TKGs) have become an effective tool for numerous intelligent applications. Due to their incompleteness, TKG embedding methods have been proposed to infer the missing temporal facts, and work by learning latent representations for entities, relations and timestamps. However, these methods primarily focus on measuring the plausibility of the whole temporal fact, and ignore the semantic property that there exists a bias between any relation and its involved entities at various time steps. In this paper, we present a novel temporal knowledge graph completion framework, which imposes relational constraints to preserve the semantic property implied in TKGs. Specifically, we borrow ideas from two well-known transformation functions, i.e., tensor decomposition and hyperplane projection, and design relational constraints associated with timestamps. We then adopt suitable regularization schemes to accommodate specific relational constraints, which combat overfitting and enforce temporal smoothness. Experimental studies indicate the superiority of our proposal compared to existing baselines on the task of temporal knowledge graph completion.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

Explore related subjects

Discover the latest articles and news from researchers in related subjects, suggested using machine learning.

Data Availability

The data that support the findings of this study are openly available at https://github.com/lmdgit/TKGs.

Notes

  1. Since KRC can be seen as an extension of the static translational models, we fine-tuned KRC by using the TTransE, the variant of translational model, as the base score function to test it on the TKG completion task.

References

  1. Mezni H (2021) Temporal knowledge graph embedding for effective service recommendation. IEEE Transactions on Services Computing. https://doi.org/10.1109/TSC.2021.3075053

  2. Bai L, Yu W, Chen M, Ma X (2021) Multi-hop reasoning over paths in temporal knowledge graphs using reinforcement learning. Applied Soft Computing. https://doi.org/10.1016/j.asoc.2021.107144https://doi.org/10.1016/j.asoc.2021.107144

  3. Deng S, Rangwala H, Ning Y (2020) Dynamic knowledge graph based multi-event forecasting. In: Proceedings of the 26th ACM SIGKDD. https://doi.org/10.1145/3394486.3403209https://doi.org/10.1145/3394486.3403209. ACM, New York, pp 1585–1595

  4. Kazemi SM, Goel R, Jain K (2020) Representation learning for dynamic graphs: a survey. Journal of Machine Learning Research

  5. Wu J, Cao M, Cheung JCK (2020) TeMP: temporal message passing for temporal knowledge graph completion. In: Proceedings of EMNLP

  6. Wang Q, Mao Z, Wang B, Guo L (2017) Knowledge graph embedding: a survey of approaches and applications. IEEE Transactions on Knowledge and Data Engineering

  7. Leblay J, Chekol MW (2018) Deriving validity time in knowledge graph. In: Proceedings of the Web conference 2018. Republic and Canton of Geneva, CHE, pp 1771–1776. https://doi.org/10.1145/3184558.3191639

  8. García-Durán A, Dumančić S, Niepert M (2018) Learning sequence encoders for temporal knowledge graph completion. In: Proceedings of EMNLP, pp 4816–4821

  9. Lacroix T, Obozinski G, Usunier N (2020) Tensor decompositions for temporal knowledge base completion. In: Proceedings of the international conference on learning representations

  10. Wang H, Ren H, Leskovec J (2021) Relational message passing for knowledge graph completion. In: Proceedings of the 27th ACM SIGKDD conference on knowledge discovery and data mining, pp 1697–1707

  11. Ji S, Pan S, Cambria E, Marttinen P, Yu PS (2021) A survey on knowledge graphs: representation, acquisition, and applications. IEEE Transactions on Neural Networks and Learning Systems

  12. Bordes A, Usunier N, Garcia-Duran A et al (2013) Translating embeddings for modeling multi-relational data. In: Proceedings of advances in neural information processing systems, pp 2787– 2795

  13. Lin Y, Liu Z, Sun M, Liu Y, Zhu X (2015) Learning entity and relation embeddings for knowledge graph completion. In: Proceedings of the 29th AAAI conference on artificial intelligence, pp 2181–2187

  14. Wang Z, Zhang J, Feng J, Chen Z (2014) Knowledge graph embedding by translating on hyperplanes. In: Proceedings of the 28th AAAI conference on artificial intelligence, pp 1112–1119

  15. Ji G, He S, Xu L, Liu K, Zhao J (2015) Knowledge graph embedding via dynamic mapping matrix. In: Proceedings of the 53rd annual meeting of the association for computational linguistics and the 7th international joint conference on natural language processing (volume 1: long papers), pp 687–696

  16. Nickel M, Tresp V, Kriegel HP (2011) A three-way model for collective learning on multi-relational data. In: Proceedings of the 28th international conference on machine learning, pp 809–816

  17. Yang B, Yih W, He X, Gao J, Deng L (2015) Embedding entities and relations for learning and inference in knowledge bases. In: Proceedings of international conference on learning representations

  18. Trouillon T, Welbl J, Riedel S, et al. (2016) Complex embeddings for simple link prediction. In: Proceedings of the 33th international conference on machine learning, pp 2071–2080

  19. Zhang Z, Li Z, Liu H, Xiong N (2020) Multi-scale dynamic convolutional network for knowledge graph embedding. IEEE Transactions on Knowledge and Data Engineering

  20. Li Z, Liu H, Zhang Z, Liu T, Xiong N (2021) Learning knowledge graph embedding with heterogeneous relation attention networks. IEEE Transactions on Neural Networks and Learning Systems

  21. Li Z, Jin X, Li W et al (2021) Temporal knowledge graph reasoning based on evolutional representation learning. In: Proceedings of SIGIR

  22. Jin W, Qu M, Jin X et al (2020) Recurrent event network: autoregressive structure inference over temporal knowledge graphs. In: Proceedings of EMNLP

  23. Zhu C, Chen M, Fan C et al (2020) Learning from history: modeling temporal knowledge graphs with sequential copy-generation networks. In: Proceedings of association for the advancement of artificial intelligence

  24. Dasgupta SS, Ray SN, Talukdar P (2018) HyTE: hyperplane-based temporally aware knowledge graph embedding. In: Proceedings of the 2018 conference on empirical methods in natural language processing

  25. Ma Y, Tresp V, Daxberger EA (2019) Embedding models for episodic knowledge graphs. Journal of Web Semantics

  26. Goel R, Kazemi SM, Brubaker M, Poupart P (2020) Diachronic embedding for temporal knowledge graph completion. In: Proceedings of association for the advancement of artificial intelligence

  27. Wu J, Cao M, Cheung J, Hamilton WL (2020) TeMP: temporal message passing for temporal knowledge graph completion. In: Proceedings of the 2020 conference on empirical methods in natural language processing

  28. Sadeghian A, Armandpour M, Colas A, Wang DZ (2021) ChronoR: rotation based temporal knowledge graph embedding. In: Proceedings of association for the advancement of artificial intelligence

  29. Shao P, Zhang D, Yang G, Tao J, Che F, Liu T (2022) Tucker decomposition-based temporal knowledge graph completion. Knowledge-Based Systems

  30. Krompaß D, Baier S, Tresp V (2015) Type-constrained representation learning in knowledge graphs. In: Proceedings of the 14th international semantic web conference, pp 640–655

  31. Li M, Sun Z, Zhang S, Zhang W (2021) Enhancing knowledge graph embedding with relational constraints. Neurocomputing 2021(429):77–88

    Google Scholar 

  32. Zhang Z, Cai J, Wang J (2020) Duality-induced regularizer for tensor factorization based knowledge graph completion. In: Proceedings of the 34th conference on neural information processing systems

  33. Lacroix T, Usunier N, Obozinski G (2018) Canonical tensor decomposition for knowledge base completion. In: Proceedings of the international conference on machine learning

  34. Trivedi R, Dai H, Wang Y et al (2017) Know-evolve: deep temporal reasoning for dynamic knowledge graphs. In: Proceedings of ICML, pp 3462–3471

  35. Boschee E, Lautenschlager J, O’Brien S et al (2015) Icews coded event data. Harvard Dataverse, 12

  36. Leetaru K, Schrodt PA (2013) Gdelt: global data on events, location, and tone. In: ISA annual convention, vol 2, pp 1–49. Citeseer

  37. Xu Y, Yang C, Sun B, Yan X, Chen M (2021) A novel multi-scale fusion framework for detail-preserving low-light image enhancement. Information Sciences

  38. Xu Y, Sun B, Yan X, Hu J, Chen M (2020) Multi-focus image fusion using learning based matting with sum of the Gaussian-based modified. Laplacian Digital Signal Processing

  39. Xu Y, Sun B (2017) Color-compensated multi-scale exposure fusion based on physical features. Optik

  40. Xu Y, Yan X, Sun B, Zhai J, Liu Z (2022) Multireceptive field denoising residual convolutional networks for fault diagnosis. IEEE Transactions on Industrial Electronics

Download references

Acknowledgements

The authors are thankful for the financial support from the National Key Research and Development Program of China (No. 2021YFF0704000) and the National Natural Science Foundation of China (Nos. 61876183, 61961160707, 61976212).

Author information

Authors and Affiliations

  1. University of Chinese Academy of Sciences (UCAS), Beijing, 100049, China

    Mingda Li, Zhengya Sun & Wensheng Zhang

  2. Research Center of Precision Sensing and Control, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China

    Mingda Li, Zhengya Sun & Wensheng Zhang

  3. Department of Automation, Beijing Information Science and Technology University, Beijing, 100192, China

    Wei Liu

Authors
  1. Mingda Li
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Zhengya Sun
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Wensheng Zhang
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Wei Liu
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Zhengya Sun.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Appendix: : Hyperparameters

Appendix: : Hyperparameters

We report here the hyperparameter settings used for TNTComplEx, ChronoR and KRC in our experiments.

Table 7 Optimal configurations of the baselines on four datasets
Full size table

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, M., Sun, Z., Zhang, W. et al. Leveraging semantic property for temporal knowledge graph completion. Appl Intell 53, 9247–9260 (2023). https://doi.org/10.1007/s10489-022-03981-8

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-022-03981-8

Keywords