Skip to main content
SpringerLink
Log in

Simplified Representation Learning Model Based on Parameter-Sharing for Knowledge Graph Completion

  • Conference paper
  • First Online:
Information Retrieval (CCIR 2019)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 11772))

Included in the following conference series:

Abstract

Knowledge graphs (KG) contain knowledge about the world and provide a structured representation of this knowledge. Current knowledge graphs contain only a small subset of what is true in the world. Knowledge Graph Completion (KGC) task aims to findin missing or errant relationships with the goal of improving the general quality of KGs. Recent years have witnessed great advance of represent learning (RL) based KGC models, which represent entities and relations as elements of a continuous vector space. However, with the deepening of the research, the scale of parameters and the complexity of KGC models become larger and larger, resulting in a serious imbalance between accuracy and computational complexity. Finally, not only the efficiency is not satisfactory, but also the training cost becomes high, which seriously restricts the flexibility and scalability of the KGC model. Therefore, this paper investigates how to enhance the simplicity of KGC model and achieve a reasonable balance between accuracy and complexity. Extensive experiments show that the proposed framework improves the performance of the current represent learning models for KGC task.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    \((h',r',t')\) usually denotes the “corrupted” triple which does not exist in \(\varDelta \).

  2. 2.

    Take the prediction of head entity h of triple (?, r, t) as example.

References

  1. Bollacker, K., Evans, C., Paritosh, P., Sturge, T., Taylor, J.: Freebase: a collaboratively created graph database for structuring human knowledge. In: SIGMOD Conference, pp. 1247–1250 (2008)

    Google Scholar 

  2. Bordes, A., Glorot, X., Weston, J., Bengio, Y.: Joint learning of words and meaning representations for open-text semantic parsing. In: AISTATS (2012)

    Google Scholar 

  3. 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, pp. 2787–2795 (2013)

    Google Scholar 

  4. Bordes, A., Weston, J., Collobert, R., Bengio, Y.: Learning structured embeddings of knowledge bases. In: AAAI Conference on Artificial Intelligence, AAAI 2011, San Francisco, California, USA, August 2011

    Google Scholar 

  5. Ding, A.A., Chen, C., Eisenbarth, T.: Simpler, faster, and more robust t-test based leakage detection. In: Standaert, F.-X., Oswald, E. (eds.) COSADE 2016. LNCS, vol. 9689, pp. 163–183. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-43283-0_10

    Chapter  Google Scholar 

  6. Dong, X., et al.: Knowledge vault: a web-scale approach to probabilistic knowledge fusion. In: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 601–610 (2014)

    Google Scholar 

  7. Hastie, T., Tibshirani, R.: Classification by pairwise coupling. In: Conference on Advances in Neural Information Processing Systems (1998)

    Article  MathSciNet  Google Scholar 

  8. Huang, H., Wang, Y., Feng, C., Liu, Z., Zhou, Q.: Leveraging conceptualization for short-text embedding. IEEE Trans. Knowl. Data Eng. 30(7), 1282–1295 (2018)

    Article  Google Scholar 

  9. Jankowski, K.R.B., Flannelly, K.J., Flannelly, L.T.: The t-test: an influential inferential tool in chaplaincy and other healthcare research. J. Health Care Chaplain. 24(1), 30 (2018)

    Article  Google Scholar 

  10. Ji, G., He, S., Xu, L., Liu, K., Zhao, J.: Knowledge graph embedding via dynamic mapping matrix. In: ACL (2015)

    Google Scholar 

  11. Jiang, M., et al.: Text classification based on deep belief network and softmax regression. Neural Comput. Appl. 7, 1–10 (2016)

    Google Scholar 

  12. Kazemi, S.M., Poole, D.: Simple embedding for link prediction in knowledge graphs. In: NeurIPS (2018)

    Google Scholar 

  13. Li, J., Li, Y., Zhai, F.: Initial fine alignment based on self-contained measurement in erection manoeuvre. IET Sci. Meas. Technol. 12(3), 375–381 (2018)

    Article  Google Scholar 

  14. Liang, Y., Xu, F., Zhang, S.H., Lai, Y.K., Mu, T.: Knowledge graph construction with structure and parameter learning for indoor scene design. Comput. Vis. Media 4(2), 1–15 (2018)

    Google Scholar 

  15. Lin, C., Fang, B., Shang, Z., Tang, Y.: Negative samples reduction in cross-company software defects prediction. Inf. Softw. Technol. 62(1), 67–77 (2015)

    Google Scholar 

  16. Lin, Y., Liu, Z., Luan, H.B., Sun, M., Rao, S., Liu, S.: Modeling relation paths for representation learning of knowledge bases. In: EMNLP (2015)

    Google Scholar 

  17. Lin, Y., Liu, Z., Zhu, X., Zhu, X., Zhu, X.: Learning entity and relation embeddings for knowledge graph completion. In: Twenty-Ninth AAAI Conference on Artificial Intelligence, pp. 2181–2187 (2015)

    Google Scholar 

  18. Ma, S., Ding, J., Jia, W., Wang, K., Guo, M.: TransT: type-based multiple embedding representations for knowledge graph completion. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pp. 717–733 (2017)

    Chapter  Google Scholar 

  19. Meilicke, C., Fink, M., Wang, Y., Ruffinelli, D., Gemulla, R., Stuckenschmidt, H.: Fine-grained evaluation of rule- and embedding-based systems for knowledge graph completion. In: Vrandečić, D., et al. (eds.) ISWC 2018. LNCS, vol. 11136, pp. 3–20. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00671-6_1

    Chapter  Google Scholar 

  20. Mikolov, T., Sutskever, I., Chen, K., Corrado, G., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems 26, pp. 3111–3119 (2013)

    Google Scholar 

  21. Nguyen, D.Q., Vu, T., Nguyen, T.D., Nguyen, D.Q., Phung, D.: A capsule network-based embedding model for knowledge graph completion and search personalization (2018)

    Google Scholar 

  22. Nguyen, D.Q., Sirts, K., Qu, L., Johnson, M.: STransE: a novel embedding model of entities and relationships in knowledge bases. In: HLT-NAACL (2016)

    Google Scholar 

  23. Nickel, M., Rosasco, L., Poggio, T.: Holographic embeddings of knowledge graphs. In: Thirtieth AAAI Conference on Artificial Intelligence, pp. 1955–1961 (2016)

    Google Scholar 

  24. Nickel, M., Rosasco, L., Poggio, T.A.: Holographic embeddings of knowledge graphs. In: AAAI (2016)

    Google Scholar 

  25. Nickel, M., Tresp, V., Kriegel, H.P.: A three-way model for collective learning on multi-relational data. In: International Conference on International Conference on Machine Learning (2011)

    Google Scholar 

  26. Qian, C., Yu, Y., Tang, K., Jin, Y., Yao, X., Zhou, Z.H.: On the effectiveness of sampling for evolutionary optimization in noisy environments. Evol. Comput. 26(2), 237–267 (2018)

    Article  Google Scholar 

  27. Quan, W., Mao, Z., Wang, B., Li, G.: Knowledge graph embedding: a survey of approaches and applications. IEEE Trans. Knowl. Data Eng. 29(12), 2724–2743 (2017)

    Article  Google Scholar 

  28. Read, J., Pfahringer, B., Holmes, G.: Multi-label classification using ensembles of pruned sets. In: Eighth IEEE International Conference on Data Mining (2008)

    Google Scholar 

  29. Read, J., Pfahringer, B., Holmes, G., Frank, E.: Classifier chains for multi-label classification. Mach. Learn. 85(3), 333–359 (2011)

    Article  MathSciNet  Google Scholar 

  30. Slatkin, M., Hudson, R.R.: Pairwise comparisons of mitochondrial dna sequences in stable and exponentially growing populations. Genetics 129(2), 555–562 (1991)

    Google Scholar 

  31. Socher, R., Chen, D., Manning, C.D., Ng, A.Y.: Reasoning with neural tensor networks for knowledge base completion. In: International Conference on Neural Information Processing Systems, pp. 926–934 (2013)

    Google Scholar 

  32. Sun, Y., Wen, G.: Ensemble softmax regression model for speech emotion recognition. Multimedia Tools & Appl. 76, 8305–8328 (2016)

    Article  Google Scholar 

  33. Trouillon, T., Welbl, J., Riedel, S., Gaussier, É., Bouchard, G.: Complex embeddings for simple link prediction (2016)

    Google Scholar 

  34. Wang, Y., Huang, H., Feng, C.: Query expansion based on a feedback concept model for microblog retrieval. In: International Conference on World Wide Web, pp. 559–568 (2017)

    Google Scholar 

  35. Wang, Y., Huang, H., Feng, C., Zhou, Q., Gu, J., Gao, X.: CSE: conceptual sentence embeddings based on attention model. In: 54th Annual Meeting of the Association for Computational Linguistics, pp. 505–515 (2016)

    Google Scholar 

  36. Wang, Z., Zhang, J., Feng, J., Chen, Z.: Knowledge graph embedding by translating on hyperplanes. In: Twenty-Eighth AAAI Conference on Artificial Intelligence, pp. 1112–1119 (2014)

    Google Scholar 

  37. Wang, Z., Li, J.: Text-enhanced representation learning for knowledge graph. In: International Joint Conference on Artificial Intelligence (2016)

    Google Scholar 

  38. Xia, F., Liu, T.Y., Wang, J., Zhang, W., Hang, L.: Listwise approach to learning to rank: theory and algorithm. In: International Conference on Machine Learning (2008)

    Google Scholar 

  39. Xiao, H., Huang, M., Meng, L., Zhu, X.: SSP: semantic space projection for knowledge graph embedding with text descriptions. In: AAAI (2017)

    Google Scholar 

  40. Xiao, H., Huang, M., Zhu, X.: TransG: a generative model for knowledge graph embedding. In: Meeting of the Association for Computational Linguistics, pp. 2316–2325 (2016)

    Google Scholar 

  41. Xie, R., Liu, Z., Jia, J.J., Luan, H., Sun, M.: Representation learning of knowledge graphs with entity descriptions. In: AAAI (2016)

    Google Scholar 

  42. Yi, T., Luu, A.T., Hui, S.C.: Non-parametric estimation of multiple embeddings for link prediction on dynamic knowledge graphs. In: Thirty First Conference on Artificial Intelligence (2017)

    Google Scholar 

  43. Yuan, Z., et al.: Softmax regression design for stochastic computing based deep convolutional neural networks. In: On Great Lakes Symposium on VLSI (2017)

    Google Scholar 

  44. Zeman, O., Tennekes, H.: A self-contained model for the pressure terms in the turbulent stress equations of the neutral atmospheric boundary layer. J. Atmos. Sci. 32(9), 1808–1813 (2010)

    Article  Google Scholar 

Download references

Acknowledgements

The authors are very grateful to the editors and reviewers for their helpful comments. This work is funded by: (i) the China Postdoctoral Science Foundation (No. 2018M641436); (ii) the Joint Advanced Research Foundation of China Electronics Technology Group Corporation (CETC) (No. 6141B08010102); (iii) 2018 Culture and tourism think tank project (No. 18ZK01); (iv) the New Generation of Artificial Intelligence Special Action Project (18116001); and (v) the Joint Advanced Research Foundation of China Electronics Technology Group Corporation (CETC) (No. 6141B0801010a).

Author information

Authors and Affiliations

  1. China Academy of Electronics and Information Technology of CETC, Beijing, China

    Yashen Wang, Huanhuan Zhang, Yifeng Li & Haiyong Xie

  2. University of Science and Technology of China, Hefei, Anhui, China

    Haiyong Xie

Authors
  1. Yashen Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Huanhuan Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yifeng Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Haiyong Xie
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yashen Wang .

Editor information

Editors and Affiliations

  1. Fudan University, Shanghai, China

    Qi Zhang

  2. Fuzhou University, Fuzhou, China

    Xiangwen Liao

  3. Shandong University, Qingdao, China

    Zhaochun Ren

Rights and permissions

Reprints and permissions

Copyright information

© 2019 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Wang, Y., Zhang, H., Li, Y., Xie, H. (2019). Simplified Representation Learning Model Based on Parameter-Sharing for Knowledge Graph Completion. In: Zhang, Q., Liao, X., Ren, Z. (eds) Information Retrieval. CCIR 2019. Lecture Notes in Computer Science(), vol 11772. Springer, Cham. https://doi.org/10.1007/978-3-030-31624-2_6

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-31624-2_6

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-31623-5

  • Online ISBN: 978-3-030-31624-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation