Abstract
Knowledge graph embedding models (KGEs) are actively utilized in many of the AI-based tasks, especially link prediction. Despite achieving high performances, one of the crucial aspects of KGEs is their capability of inferring relational patterns, such as symmetry, antisymmetry, inversion, and composition. Among the many reasons, the inference capability of embedding models is highly affected by the used loss function. However, most of the existing models failed to consider this aspect in their inference capabilities. In this paper, we show that disregarding loss functions results in inaccurate or even wrong interpretation from the capability of the models. We provide deep theoretical investigations of the already exiting KGE models on the example of the TransE model. To the best of our knowledge, so far, this has not been comprehensively investigated. We show that by a proper selection of the loss function for training a KGE e.g., TransE, the main inference limitations are mitigated. The provided theories together with the experimental results confirm the importance of loss functions for training KGE models and improving their performance.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bordes, A., Usunier, N., Garcia-Duran, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: NIPS Conference, pp. 2787–2795 (2013)
Dettmers, T., Minervini, P., Stenetorp, P., Riedel, S.: Convolutional 2D knowledge graph embeddings. In: Thirty-Second AAAI Conference (2018)
Ebisu, T., Ichise, R.: Toruse: knowledge graph embedding on a lie group. In: Thirty-Second AAAI Conference (2018)
Feng, J., Huang, M., Wang, M., Zhou, M., Hao, Y., Zhu, X.: Knowledge graph embedding by flexible translation. In: KR Conference (2016)
Ji, G., He, S., Xu, L., Liu, K., Zhao, J.: Knowledge graph embedding via dynamic map** 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), vol. 1, pp. 687–696 (2015)
Kazemi, S.M., Poole, D.: Simple embedding for link prediction in knowledge graphs. In: NIPS Conference, pp. 4284–4295 (2018)
Lin, Y., Liu, Z., Sun, M., Liu, Y., Zhu, X.: Learning entity and relation embeddings for knowledge graph completion. In: Twenty-Ninth AAAI Conference (2015)
Nayyeri, M., Vahdati, S., Lehmann, J., Shariat Yazdi, H.: Soft marginal TransE for scholarly knowledge graph completion. ar**v preprint ar**v:1904.12211 (2019)
Nguyen, D.Q., Sirts, K., Qu, L., Johnson, M.: Stranse: a novel embedding model of entities and relationships in knowledge bases. ar**v preprint ar**v:1606.08140 (2016)
Ruffinelli, D., Broscheit, S., Gemulla, R.: You can teach an old dog new tricks! on training knowledge graph embeddings. In: International Conference on Learning Representations (2019)
Sun, Z., Deng, Z.H., Nie, J.Y., Tang, J.: Rotate: knowledge graph embedding by relational rotation in complex space. ar**v preprint ar**v:1902.10197 (2019)
Toutanova, K., Chen, D.: Observed versus latent features for knowledge base and text inference. In: Proceedings of the 3rd Workshop on Continuous Vector Space Models and their Compositionality, pp. 57–66 (2015)
Wang, Q., Mao, Z., Wang, B., Guo, L.: Knowledge graph embedding: a survey of approaches and applications. IEEE Trans. Knowl. Data Eng. 29(12), 2724–2743 (2017)
Wang, Y., Gemulla, R., Li, H.: On multi-relational link prediction with bilinear models. In: Thirty-Second AAAI Conference (2018)
Wang, Z., Zhang, J., Feng, J., Chen, Z.: Knowledge graph embedding by translating on hyperplanes. In: Twenty-Eighth AAAI Conference (2014)
Zhou, X., Zhu, Q., Liu, P., Guo, L.: Learning knowledge embeddings by combining limit-based scoring loss. In: Proceedings of the 2017 ACM CIKM Conference, pp. 1009–1018. ACM (2017)
Acknowledgements
We acknowledge the support of the EU projects TAILOR (GA 952215), Cleopatra (GA 812997), the BmBF project MLwin, the EU Horizon 2020 grant 809965, and ScaDS.AI (01/S18026A-F).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Nayyeri, M. et al. (2021). Loss-Aware Pattern Inference: A Correction on the Wrongly Claimed Limitations of Embedding Models. In: Karlapalem, K., et al. Advances in Knowledge Discovery and Data Mining. PAKDD 2021. Lecture Notes in Computer Science(), vol 12714. Springer, Cham. https://doi.org/10.1007/978-3-030-75768-7_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-75768-7_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-75767-0
Online ISBN: 978-3-030-75768-7
eBook Packages: Computer ScienceComputer Science (R0)