Abstract
The qualifiers (key-value pairs) in the hyper-relational knowledge graphs (HKGs) help the model accurately identify the target. The primary challenge of HKG is how to efficiently obtain the independent features of entities and relations from qualifiers, which can be utilized to address the issue of their potential confusion with the main triples. However, most current models for HKG utilize identical embedding matrices to represent entities within both main triples and qualifiers, making it hard to capture the precise influence of various qualifiers on relations. To address these issues, we propose an improved model IRE for HKG representation. IRE independently learns the embeddings of qualifiers, which promotes exploring interactions and features between qualifiers and main triples. Then, IRE leverages these features to enhance the semantic richness of relations. We incorporate contrastive learning to distinguish entities and relations with unique semantics further, enhancing the model’s learning capabilities. IRE can be applied to various downstream tasks, and we conducted experiments using the link prediction task. Experimental evaluations of multiple datasets demonstrate that the IRE consistently outperforms several state-of-the-art baselines.
This is a preview of subscription content, log in via an institution to check access.
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, vol. 26, p. 2787–2795 (2013)
Galkin, M., Trivedi, P., Maheshwari, G., Usbeck, R., Lehmann, J.: Message passing for hyper-relational knowledge graphs. In: Proceedings of the 2020 Conference on EMNLP, pp. 7346–7359 (2020)
Guan, S., Jin, X., Guo, J., Wang, Y., Cheng, X.: Neuinfer: knowledge inference on n-ary facts. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 6141–6151 (2020)
Guan, S., Jin, X., Guo, J., Wang, Y., Cheng, X.: Link prediction on n-ary relational data based on relatedness evaluation. IEEE Trans. Knowl. Data Eng. 672–685 (2021)
Guan, S., Jin, X., Wang, Y., Cheng, X.: Link prediction on n-ary relational data. In: The World Wide Web Conference, pp. 583–593 (2019)
Ji, S., Pan, S., Cambria, E., Marttinen, P., Yu, P.S.: A survey on knowledge graphs: Representation, acquisition, and applications. IEEE Trans. Neural Netw. Learn. Syst., 494–514 (2022)
Kumar, A., Singh, S.S., Singh, K., Biswas, B.: Link prediction techniques, applications, and performance: a survey. Phys. A: Statist. Mech. Appli., 124289 (2020)
Möller, C., Lehmann, J., Usbeck, R.: Survey on english entity linking on wikidata: datasets and approaches. Semantic Web, 925–966 (2022)
Nickel, M., Rosasco, L., Poggio, T.: Holographic embeddings of knowledge graphs. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 1 (2016)
Rosso, P., Yang, D., Cudré-Mauroux, P.: Beyond triplets: hyper-relational knowledge graph embedding for link prediction. In: Proceedings of The Web Conference 2020, pp. 1885–1896 (2020)
Shen, T., Zhang, F., Cheng, J.: A comprehensive overview of knowledge graph completion. Knowl. Based Syst., 109597 (2022)
Sun, Z., Deng, Z.H., Nie, J.Y., Tang, J.: Rotate: knowledge graph embedding by relational rotation in complex space. In: International Conference on Learning Representations (2019)
Vaswani, A., et al.: Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 6000–6010 (2017)
Wang, C., Wang, X., Li, Z., Chen, Z., Li, J.: Hyconve: a novel embedding model for knowledge hypergraph link prediction with convolutional neural networks. In: Proceedings of the ACM Web Conference 2023, pp. 188–198 (2023)
Wen, J., Li, J., Mao, Y., Chen, S., Zhang, R.: On the representation and embedding of knowledge bases beyond binary relations. In: Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, pp. 1300–1307 (2016)
Xiong, B., Nayyer, M., Pan, S., Staab, S.: Shrinking embeddings for hyper-relational knowledge graphs. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, pp. 13306–13320 (2023)
Yan, Y., Zhang, M., Xu, C.: The graph attention network in relational reasoning based on knowledge graph. In: ICCVDM, pp. 698–703 (2024)
Yu, D., Yang, Y.: Improving hyper-relational knowledge graph completion. arXiv preprint arXiv:2104.08167 (2021)
Zhang, R., Li, J., Mei, J., Mao, Y.: Scalable instance reconstruction in knowledge bases via relatedness affiliated embedding. In: Proceedings of the 2018 World Wide Web Conference, pp. 1185–1194 (2018)
Zhang, W., Paudel, B., Zhang, W., Bernstein, A., Chen, H.: Interaction embeddings for prediction and explanation in knowledge graphs. In: Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining. pp. 96–104 (2019)
Acknowledgement
This work was supported by the Heilongjiang Key R&D Program of China under Grant No. GA23A915 and the National Natural Science Foundation of China under Grant No. 62302120.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Han, Q., Li, J., Lu, D., Li, L., Xie, B. (2024). Independent Embedding-Based Relational Enhancement Model for Hyper-Relational Knowledge Graph. In: Onizuka, M., et al. Database Systems for Advanced Applications. DASFAA 2024. Lecture Notes in Computer Science, vol 14853. Springer, Singapore. https://doi.org/10.1007/978-981-97-5562-2_33
Download citation
DOI: https://doi.org/10.1007/978-981-97-5562-2_33
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-5561-5
Online ISBN: 978-981-97-5562-2
eBook Packages: Computer ScienceComputer Science (R0)