More Is Better: Sequential Combinations of Knowledge Graph Embedding Approaches

  • Kemas Wiharja
  • Jeff Z. PanEmail author
  • Martin Kollingbaum
  • Yu Deng
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11341)


Constructing and maintaining large-scale good quality knowledge graphs present many challenges. Knowledge graph completion has been regarded a promising direction in the knowledge graph community. The majority of current work for knowledge graph completion approaches do not take the schema of a target knowledge graph as input. As a result, the triples generated by these approaches are not necessarily consistent with the schema of the target knowledge graph. This paper proposes to improve the correctness of knowledge graph completion based on Schema Aware Triple Classification (SATC), which enables sequential combinations of knowledge graph embedding approaches. Extensive experiments show that our proposed approaches can significantly improve the correctness of the new triples produced by knowledge graph embedding methods.


Knowledge graph Embedding Schema aware triple classification Knowledge representation and reasoning Approximate reasoning Artificial Intelligence 



This work was supported by IBM Faculty Award and the EU Marie Currie K-Drive project (286348). Kemas Wiharja was also supported by the Lembaga Pengelola Dana Pendidikan (LPDP), the Ministry of Finance of Indonesia.


  1. 1.
    Pan, J.Z., Vetere, G., Gomez-Perez, J.M., Wu, H. (eds.): Exploiting Linked Data and Knowledge Graphs for Large Organisations. Springer, Cham (2017). ISBN 978-3-319-45652-2CrossRefGoogle Scholar
  2. 2.
    Pan, J.Z., et al. (eds.): Reasoning Web 2016. LNCS, vol. 9885. Springer, Cham (2017). Scholar
  3. 3.
    Paulheim, H.: Knowledge graph refinement: a survey of approaches and evaluation methods. Semant. Web J. 8, 489–508 (2016)CrossRefGoogle Scholar
  4. 4.
    Xiong, W., Hoang, T., Wang, W.Y.: DeepPath: a reinforcement learning method for knowledge graph reasoning. In: EMNLP (2017)Google Scholar
  5. 5.
    Bordes, A., Usunier, N., Garcia-Duran, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: Advances in Neural Information Processing Systems 26, pp. 2787–2795. Curran Associates Inc. (2013)Google Scholar
  6. 6.
    Pan, J.Z., Thomas, E.: Approximating OWL-DL ontologies. In: AAAI 2007, pp. 1434–1439 (2007)Google Scholar
  7. 7.
    Pan, J.Z., Ren, Y., Zhao, Y.: Tractable approximate deduction for OWL. Artif. Intell. 235, 95–155 (2016)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Lin, Y., Liu, Z., Sun, M., Liu, Y., Zhu, X.: Learning entity and relation embeddings for knowledge graph completion. In: Proceedings of 29th AAAI Conference on Artificial Intelligence, pp. 2181–2187 (2015)Google Scholar
  9. 9.
    Wang, Z., Zhang, J., Feng, J., Chen, Z.: Knowledge graph embedding by translating on hyperplanes. In: Proceedings of 28th AAAI Conference on Artificial Intelligence, pp. 1112–1119 (2014)Google Scholar
  10. 10.
    Nguyen, D.Q., Sirts, K., Qu, L., Johnson, M.: STransE: a novel embedding model of entities and relationships in knowledge bases. In: Proceedings Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 460–466 (2016)Google Scholar
  11. 11.
    Xiao, H., Huang, M., Zhu, X.: TransG: a generative model for knowledge graph embedding. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), vol. 1, pp. 2316–2325 (2016)Google Scholar
  12. 12.
    Socher, R., Chen, D., Manning, C.D., Ng, A.Y.: Reasoning with neural tensor networks for knowledge base completion. In: Proceedings of Neural Information Processing Systems, pp. 926–934 (2013)Google Scholar
  13. 13.
    Guo, S., Ding, B., Wang, Q., Wang, L., Wang, B.: Knowledge base completion via rule-enhanced relational learning. In: Chen, H., Ji, H., Sun, L., Wang, H., Qian, T., Ruan, T. (eds.) CCKS 2016. CCIS, vol. 650, pp. 219–227. Springer, Singapore (2016). Scholar
  14. 14.
    Du, J., Qi, K., Wan, H., Peng, B., Lu, S., Shen, Y.: Enhancing knowledge graph embedding from a logical perspective. In: Wang, Z., Turhan, A.-Y., Wang, K., Zhang, X. (eds.) JIST 2017. LNCS, vol. 10675, pp. 232–247. Springer, Cham (2017). Scholar
  15. 15.
    Nickel, M., Tresp, V., Kriegel, H.-P.: A three-way model for collective learning on multi-relational data. In: Proceedings of 28th International Conference on Machine Learning, pp. 809–816 (2011)Google Scholar
  16. 16.
    Jenatton, R., Roux, N.L., Bordes, A., Obozinski, G.R.: A latent factor model for highly multi-relational data. In: Proceedings of Neural Information Processing Systems, pp. 3167–3175 (2012)Google Scholar
  17. 17.
    Glorot, X., Bordes, A., Weston, J., Bengio, Y.: A semantic matching energy function for learning with multi-relational data. Mach. Learn. 94(2), 233–259 (2014)MathSciNetCrossRefGoogle Scholar
  18. 18.
    Paulheim, H., Bizer, C.: Improving the quality of linked data using statistical distributions. Int. J. Semant. Web Inf. Syst. (IJSWIS) 10(2), 63–86 (2014)CrossRefGoogle Scholar
  19. 19.
    Wang, Z., Zhang, J., Feng, J., Chen, Z.: Knowledge graph embedding by translating on hyperplanes. In: AAAI Conference on Artificial Intelligence (2014)Google Scholar
  20. 20.
    Mitchell, T., et al.: Never ending learning. In: AAAI Conference on Artificial Intelligence, pp. 2302–2310 (2015)Google Scholar
  21. 21.
    Liu, S., d’Aquin, M., Motta, E.: Measuring accuracy of triples in knowledge graphs. In: Gracia, J., Bond, F., McCrae, J.P., Buitelaar, P., Chiarcos, C., Hellmann, S. (eds.) LDK 2017. LNCS (LNAI), vol. 10318, pp. 343–357. Springer, Cham (2017). Scholar
  22. 22.
    Shi, B., Weninger, T.: Open-world knowledge graph completion. arXiv preprint arXiv:1711.03438 (2017)
  23. 23.
    Du, J., Qi, K., Shen, Y.: Knowledge graph embedding with logical consistency. Guangdong University of Foreign Studies (2018, unpublished paper)Google Scholar
  24. 24.
    Meilicke, C., Ruffinelli, D., Nolle, A., Paulheim, H., Stuckenschmidt, H.: Fast ABox consistency checking using incomplete reasoning and caching. In: Costantini, S., Franconi, E., Van Woensel, W., Kontchakov, R., Sadri, F., Roman, D. (eds.) RuleML+RR 2017. LNCS, vol. 10364, pp. 168–183. Springer, Cham (2017). Scholar
  25. 25.
    Paulheim, H., Stuckenschmidt, H.: Fast approximate A-Box consistency checking using machine learning. In: Sack, H., Blomqvist, E., d’Aquin, M., Ghidini, C., Ponzetto, S.P., Lange, C. (eds.) ESWC 2016. LNCS, vol. 9678, pp. 135–150. Springer, Cham (2016). Scholar
  26. 26.
    Ruffinelli, D.: Towards scalable ontological reasoning using machine learning. In: CEUR Workshop Proceedings, vol. 1875, Paper-5. RWTH (2017)Google Scholar
  27. 27.
    Horridge, M., Bechhofer, S.: The OWL API: a Java API for working with OWL 2 ontologies. In: Proceedings of the 6th International Conference on OWL: Experiences and Directions, vol. 529, pp. 49–58. CEUR-WS. org, October 2009Google Scholar
  28. 28.
    Ringsquandl, M., et al.: Event-enhanced learning for KG completion. In: Gangemi, A., et al. (eds.) ESWC 2018. LNCS, vol. 10843, pp. 541–559. Springer, Cham (2018). Scholar
  29. 29.
    Tran, H.D., Stepanova, D., Gad-Elrab, M.H., Lisi, F.A., Weikum, G.: Towards nonmonotonic relational learning from knowledge graphs. In: Cussens, J., Russo, A. (eds.) ILP 2016. LNCS (LNAI), vol. 10326, pp. 94–107. Springer, Cham (2017). Scholar
  30. 30.
    Ho, V.T., Stepanova, D., Gad-Elrab, M.H., Kharlamov, E., Weikum, G.: Rule learning from knowledge graphs guided by embedding models. In: Vrandečić, D., et al. (eds.) ISWC 2018. LNCS, vol. 11136, pp. 72–90. Springer, Cham (2018). Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Kemas Wiharja
    • 1
  • Jeff Z. Pan
    • 1
    Email author
  • Martin Kollingbaum
    • 1
  • Yu Deng
    • 2
  1. 1.Department of Computing ScienceUniversity of AberdeenAberdeenUK
  2. 2.IBM ResearchNew YorkUSA

Personalised recommendations