Advertisement

Learning from High-Degree Entities for Knowledge Graph Modeling

  • Tienan Zhang
  • Fangfang LiuEmail author
  • Yan Shen
  • Honghao Gao
  • Jing Duan
Conference paper
Part of the Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering book series (LNICST, volume 268)

Abstract

Knowledge base (KB) completion aims to infer missing facts based on existing ones in a KB. Many approaches firstly suppose that the constituents themselves (e.g., head, tail entity and relation) of a fact meet some formulas and then minimize the loss of formula to obtain the feature vectors of entities and relations. Due to the sparsity of KB, some methods also take into consideration the indirect relations between entities. However, indirect relations further widen the differences of training times of high-degree entities (entities linking by many relations) and low-degree entities. This results in underfitting of low-degree entities. In this paper, we propose the path-based TransE with aggregation (PTransE-ag) to fine-tune the feature vector of an entity by comparing it to its related entities that linked by the same relations. In this way, low-degree entities can draw useful information from high-degree entities to directly adjust their representations. Conversely, the overfitting of high-degree entities can be relieved. Extensive experiments carried on the real world dataset show our method can define entities more accurately, and inferring is more effectively than in previous methods.

Keywords

KB completion Entity degree Indirect relation Entity prediction Relation weakening 

Notes

Acknowledgements

This work is supported by National Key Research and Development Plan of China under Grant No. 2017YFD0400101, and National Natural Science Foundation of China under Grant No. 61502294, and Natural Science Foundation of Shanghai under Grant No. 16ZR1411200.

The url of the source code is https://github.com/IdelCoder/PTransE-ag.

References

  1. 1.
    Evans, C., Paritosh, P., Sturge, T., Bollacker, K., Taylor, J.: Freebase: a collaboratively created graph database for structuring human knowledge. In: Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data, pp. 1247–1250 (2008)Google Scholar
  2. 2.
    Miller, G.A.: WordNet: a lexical database for English. Future Gener. Comput. Syst. 38(11), 39–41 (1995)Google Scholar
  3. 3.
    Jakob, M., Mendes, P.N., Bizer, C.: DBpedia: a multilingual cross-domain knowledge base. In: Proceedings of Language Resources and Evaluation, pp. 1813–1817 (2012)Google Scholar
  4. 4.
    Zhou, M., Nastase, V.: Using patterns in knowledge graphs for targeted information extraction. In: KBCOM 2018 (2018)Google Scholar
  5. 5.
    Gesmundo, A., Hall, K.: Projecting the knowledge graph to syntactic parsing. In: Proceedings of Conference of the European Chapter of the Association for Computational Linguistics, pp. 28–32 (2014)Google Scholar
  6. 6.
    Singh, K., Diefenbach, D., Maret, P.: WDAqua-core1: a question answering service for RDF knowledge bases. In: WWW 2018 Companion (2018)Google Scholar
  7. 7.
    Usunier, N., Garcia, A., Weston, J., Bordes, A., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: Proceedings of International Conference on Neural Information Processing Systems, pp. 2787–2795 (2013)Google Scholar
  8. 8.
    Zhang, J., Feng, J., Wang, Z., Chen, Z.: Knowledge graph embedding by translating on hyperplanes. In: Proceedings of AAAI Conference on Artificial Intelligence, pp. 1112–1119 (2014)Google Scholar
  9. 9.
    Liu, Z., Luan, H., Sun, M., Rao, S., Lin, Y., Liu, S.: Modeling relation paths for representation learning of knowledge bases. In: Proceedings of Conference on Empirical Methods in Natural Language Processing, pp. 705–714 (2015)Google Scholar
  10. 10.
    Mitchell, T., Lao, N., Cohen, W.W.: Random walk inference and learning in a large scale knowledge base. In: Proceedings of Conference on Empirical Methods in Natural Language Processing, pp. 27–31 (2011)Google Scholar
  11. 11.
    Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. Mach. Learn. 9, 249–256 (2010)Google Scholar
  12. 12.
    Weston, J., Collobert, R., Bordes, A., Bengio, Y.: Learning structured embeddings of knowledge bases. In: Proceedings of AAAI Conference on Artificial Intelligence, pp. 301–306 (2011)Google Scholar
  13. 13.
    Liu, Z., Lin, Y., Zhu, X.: Learning entity and relation embeddings for knowledge graph completion. In: Proceedings of AAAI Conference on Artificial Intelligence, pp. 2187–2195 (2015)Google Scholar
  14. 14.
    Tresp, V., Nickel, M., Kriegel, H.P.: A three-way model for collective learning on multi-relational data. In: Proceedings of International Conference on Machine Learning, pp. 809–816 (2011)Google Scholar
  15. 15.
    Liu, K., He, S., Ji, G., Zhao, J.: Knowledge graph completion with adaptive sparse transfer matrix. In: Proceedings of AAAI Conference on Artificial Intelligence, pp. 985–991 (2016)Google Scholar
  16. 16.
    Huang, M., Xiao, H., Zhu, X.: TransG: a generative model for knowledge graph embedding. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pp. 2316–2325 (2016)Google Scholar
  17. 17.
    Liu, Z., Lin, Y., Sun, M.: Knowledge representation learning with entities, attributes and relations. In: Proceedings of International Joint Conference on Artificial Intelligence, pp. 2866–2872 (2016)Google Scholar
  18. 18.
    He, S., Xu, L., Liu, K., Ji, G., Zhao, J.: Knowledge graph embedding via dynamic mapping matrix. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics, pp. 687–696 (2015)Google Scholar
  19. 19.
    Huang, M., Yu, H., Xiao, H., Zhu, X.: TransA: an adaptive approach for knowledge graph embedding (2015)Google Scholar
  20. 20.
    Jia, Y., Zhu, J., Qiao, J.: Modeling the correlations of relations for knowledge graph embedding. J. Comput. Sci. Technol. 33(2), 323–334 (2018)MathSciNetCrossRefGoogle Scholar
  21. 21.
    Wang, Q., Xu, W., Li, W., Zhang, M., Sun, S.: Discriminative path-based knowledge graph embedding for precise link prediction. In: Pasi, G., Piwowarski, B., Azzopardi, L., Hanbury, A. (eds.) ECIR 2018. LNCS, vol. 10772, pp. 276–288. Springer, Cham (2018).  https://doi.org/10.1007/978-3-319-76941-7_21CrossRefGoogle Scholar
  22. 22.
    Liang, Y., Giunchiglia, F., Feng, X., Lin, X., Guan, R.: Relation path embedding in knowledge graphs. Neural Comput. Appl. 1–11 (2018)Google Scholar
  23. 23.
    Rong, E., Zhuo, H., Wang, M., Zhu, H.: Embedding knowledge graphs based on transitivity and asymmetry of rules. xplan-lab.org (2018)Google Scholar
  24. 24.
    Kalman, D.: A singularly valuable decomposition: the SVD of a matrix. Coll. Math. J. 27(1), 2–23 (1996)MathSciNetCrossRefGoogle Scholar

Copyright information

© ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2019

Authors and Affiliations

  • Tienan Zhang
    • 1
  • Fangfang Liu
    • 1
    Email author
  • Yan Shen
    • 1
  • Honghao Gao
    • 1
    • 2
  • Jing Duan
    • 1
  1. 1.School of Computer Engineering and ScienceShanghai UniversityShanghaiChina
  2. 2.Computing CenterShanghai UniversityShanghaiChina

Personalised recommendations