Skip to main content
SpringerLink
Log in

Dihedron Algebraic Embeddings for Spatio-Temporal Knowledge Graph Completion

  • Conference paper
  • First Online:
The Semantic Web (ESWC 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13261))

Included in the following conference series:

Abstract

Many knowledge graphs (KG) contain spatial and temporal information. Most KG embedding models follow triple-based representation and often neglect the simultaneous consideration of the spatial and temporal aspects. Encoding such higher dimensional knowledge necessitates the consideration of true algebraic and geometric aspects. Hypercomplex algebra provides the foundation of a well defined mathematical system among which the Dihedron algebra with its rich framework is suitable to handle multidimensional knowledge. In this paper, we propose an embedding model that uses Dihedron algebra for learning such spatial and temporal aspects. The evaluation results show that our model performs significantly better than other adapted models.

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 69.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 89.99
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.

    https://www.dbpedia.org/resources/latest-core/.

  2. 2.

    https://grafana.wikimedia.org/d/000000175/wikidata-datamodel-statements?orgId=1&refresh=30m.

  3. 3.

    https://github.com/mojtabanayyeri/Spatio-temporal-KGEs.

References

  1. Balažević, I., Allen, C., Hospedales, T.M.: Tucker: Tensor factorization for knowledge graph completion. arXiv preprint (2019). arXiv:1901.09590

  2. Bordes, A., Usunier, N., Garcia-Duran, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: Neural Information Processing Systems (NIPS), pp. 1–9 (2013)

    Google Scholar 

  3. Chami, I., Wolf, A., Juan, D.-C., Sala, F., Ravi, S., Ré, C.: Low-dimensional hyperbolic knowledge graph embeddings. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 6901–6914 (2020)

    Google Scholar 

  4. Dasgupta, S.S., Ray, S.N., Talukdar, P.: Hyte: hyperplane-based temporally aware knowledge graph embedding. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 2001–2011 (2018)

    Google Scholar 

  5. Dettmers, T., Minervini, P., Stenetorp, P., Riedel, S.: Convolutional 2d knowledge graph embeddings. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)

    Google Scholar 

  6. García-Durán, A., Dumančić, S., Niepert, M.: Learning sequence encoders for temporal knowledge graph completion. arXiv preprint (2018). arXiv:1809.03202

  7. Hobbs, J., Blythe, J., Chalupsky, H., Russ, T.A.: A survey of geospatial resources, representation and reasoning. Public Distribution of the University of Southern California (2006)

    Google Scholar 

  8. Ji, G., He, S., Xu, L., Liu, K., Zhao, J.: 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 (vol. 1: Long Papers), pp. 687–696 (2015)

    Google Scholar 

  9. Ji, S., Pan, S., Cambria, E., Marttinen, P., Philip, S.Y.: A survey on knowledge graphs: representation, acquisition, and applications. IEEE Trans. Neural Netw. Learn. Syst. (2021)

    Google Scholar 

  10. Jin, W., Zhang, C., Szekely, P., Ren, X.: Recurrent event network for reasoning over temporal knowledge graphs. arXiv preprint (2019). arXiv:1904.05530

  11. Kingma, D.P., Adam, J.Ba.: A method for stochastic optimization. arXiv preprint (2014). arXiv:1412.6980

  12. Lacroix, T., Obozinski, G., Usunier, N.: Tensor decompositions for temporal knowledge base completion. arXiv preprint (2020). arXiv:2004.04926

  13. Lacroix, T., Usunier, N., Obozinski, G.: Canonical tensor decomposition for knowledge base completion. In: International Conference on Machine Learning, pp. 2863–2872. PMLR (2018)

    Google Scholar 

  14. Leblay, J., Chekol, M.W.: Deriving validity time in knowledge graph. In: Companion Proceedings of the Web Conference 2018, pp. 1771–1776 (2018)

    Google Scholar 

  15. Lehmann, J., et al.: Dbpedia-a large-scale, multilingual knowledge base extracted from wikipedia, vol. 6, pp. 167–195 (2015, IOS Press)

    Google Scholar 

  16. Leidner, J.L.: A survey of textual data & geospatial technology. In: Werner, M. (ed.) Handbook of Big Geospatial Data, pp. 429–457. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-55462-0_16

    Chapter  Google Scholar 

  17. Li, Z., Liu, H., Zhang, Z., Liu, T., Xiong, N.N.: Learning knowledge graph embedding with heterogeneous relation attention networks. IEEE Trans. Neural Netw. Learn. Syst. (2021)

    Google Scholar 

  18. Lin, Y., Liu, Z., Sun, M., Liu, Y., Zhu, X.: Learning entity and relation embeddings for knowledge graph completion. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 29 (2015)

    Google Scholar 

  19. Ma, Y., Tresp, V., Daxberger, E.A.: Embedding models for episodic knowledge graphs. J. Web Semant. 59, 100490 (2019)

    Article  Google Scholar 

  20. Mahdisoltani, F., Biega, J., Suchanek, F.: Yago3: a knowledge base from multilingual wikipedias. In: 7th Biennial Conference on Innovative Data Systems Research. CIDR Conference (2014)

    Google Scholar 

  21. Nayyeri, M., Vahdati, S., Aykul, C., Lehmann, J.: 5* knowledge graph embeddings with projective transformations. arXiv preprint (2020). arXiv:2006.04986

  22. Qian, T., Liu, B., Nguyen, Q.V.H., Yin, H.: Spatiotemporal representation learning for translation-based poi recommendation. ACM Trans. Inf. Syst. (TOIS) 37(2), 1–24 (2019)

    Article  Google Scholar 

  23. Rotman, J.J.: Advanced Modern Algebra, vol. 114. American Mathematical Soc, New York (2010)

    MATH  Google Scholar 

  24. Sun, Z., Deng, Z.-H., Nie, J.-Y., Tang, J.: Rotate: knowledge graph embedding by relational rotation in complex space. arXiv preprint (2019). arXiv:1902.10197

  25. Pellissier Tanon, T., Weikum, G., Suchanek, F.: YAGO 4: a reason-able knowledge base. In: Harth, A. (ed.) ESWC 2020. LNCS, vol. 12123, pp. 583–596. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-49461-2_34

    Chapter  Google Scholar 

  26. Trouillon, T., Welbl, J., Riedel, S., Gaussier, É., Bouchard, G.: Complex embeddings for simple link prediction. In: International Conference on Machine Learning, pp. 2071–2080. PMLR (2016)

    Google Scholar 

  27. Vrandečić, D., Krötzsch, M.: Wikidata: a free collaborative knowledgebase. Commun. ACM 57(10), 78–85 (2014)

    Article  Google Scholar 

  28. Wang, Z., Zhang, J., Feng, J., Chen, Z.: Knowledge graph embedding by translating on hyperplanes. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 28 (2014)

    Google Scholar 

  29. Wildberger, N.J.: The geometry of the dihedrons (and quaternions). https://www.youtube.com/watch?v=qcmH0iKRF2w&t=1569s. Accessed 11 June 2021

  30. Xu , C., Li, R.: Relation embedding with dihedral group in knowledge graph. arXiv preprint (2019). arXiv:1906.00687

  31. Xu, C., Nayyeri, M., Alkhoury, F., Yazdi, H.S., Lehmann, J.: A time-aware knowledge graph embedding via temporal rotation. arXiv preprint (2020). arXiv:2010.01029

  32. Yang, B., Yih, W.-T., He, X., Gao, J., Deng, L.: Embedding entities and relations for learning and inference in knowledge bases. arXiv preprint (2014). arXiv:1412.6575

  33. Zhang, S., Tay, Y., Yao, L., Liu, Q.: Quaternion knowledge graph embeddings. arXiv preprint (2019). arXiv:1904.10281

  34. Zhao, L., Deng, H., Qiu, L., Li, S., Hou, Z., Sun, H., Chen, Y.: Urban multi-source spatio-temporal data analysis aware knowledge graph embedding. Symmetry 12(2), 199 (2020)

    Article  Google Scholar 

Download references

Acknowledgement

We acknowledge the support of the following projects: SPEAKER (BMWi FKZ 01MK20011A), JOSEPH (Fraunhofer Zukunftsstiftung), the EU projects Cleopatra (GA 812997), PLATOON(GA 872592), TAILOR(EU GA 952215), CALLISTO(101004152), the BMBF projects MLwin(01IS18050) and the BMBF excellence clusters ML2R (BmBF FKZ 01 15 18038 A/B/C) and ScaDS.AI (IS18026A-F).

Author information

Authors and Affiliations

  1. University of Bonn, Bonn, Germany

    Mojtaba Nayyeri, Md Tansen Khan & Jens Lehmann

  2. Institute for Applied Informatics (InfAI), Dresden, Germany

    Sahar Vahdati, Mirza Mohtashim Alam & Lisa Wenige

  3. Institute for Telecommunications (INT), TH Köln, Cologne, Germany

    Andreas Behrend

  4. Fraunhofer IAIS, Dresden, Germany

    Jens Lehmann

  5. University of Stuttgart, Stuttgart, Germany

    Mojtaba Nayyeri

Authors
  1. Mojtaba Nayyeri
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sahar Vahdati
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Md Tansen Khan
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Mirza Mohtashim Alam
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Lisa Wenige
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Andreas Behrend
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Jens Lehmann
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Md Tansen Khan .

Editor information

Editors and Affiliations

  1. University of Amsterdam, Amsterdam, Noord-Holland, The Netherlands

    Paul Groth

  2. Universidad Simón Bolívar, Leibniz Information Centre for Science and Technology, Hannover, Niedersachsen, Germany

    Maria-Esther Vidal

  3. Institut Polytechnique de Paris "DIG", Télécom ParisTech, Palaiseau, France

    Fabian Suchanek

  4. University of Southern California, Marina del Rey, CA, USA

    Pedro Szekley

  5. IBM Research - Thomas J. Watson Research, Yorktown Heights, NY, USA

    Pavan Kapanipathi

  6. LaSIGE, Fac de Ciencias,Edif C6, Pis0 3, Universidade de Lisboa, Lisbon, Portugal

    Catia Pesquita

  7. University of Nantes, Nantes, France

    Hala Skaf-Molli

  8. Aalto University, Espoo, Finland

    Minna Tamper

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Nayyeri, M. et al. (2022). Dihedron Algebraic Embeddings for Spatio-Temporal Knowledge Graph Completion. In: Groth, P., et al. The Semantic Web. ESWC 2022. Lecture Notes in Computer Science, vol 13261. Springer, Cham. https://doi.org/10.1007/978-3-031-06981-9_15

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-06981-9_15

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-06980-2

  • Online ISBN: 978-3-031-06981-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation