Abstract
Learning hyper-relational knowledge graph (HKG) representation has attracted growing interest from research communities recently. HKGs are typically organized as structured triples associating with additional qualifiers (i.e., key-value pairs) to provide unambiguous hyper-relational facts. The main challenge of HKG is to disambiguate representations of entities and relations by addressing different qualifiers. However, most current models for HKG representation are trained based on single-grained encoders, usually with fine-grained entities, relations, keys, and values in qualifiers, which makes it hard to learn the precise impact of the qualifiers on the whole triple. To overcome this problem, we propose a novel model HEAT for HKG representation by exploring multi-grained encoding, including coarse-grained and fine-grained encoding. Specifically, HEAT performs a graph coarsening method to treat each triple as an integrated coarse-grained node, which satisfies the correlation constraint between the triple and its corresponding qualifiers. Then HEAT leverages a two-stage graph encoder to encode the fine-grained element nodes and coarse-grained triple nodes. The experimental results on three datasets demonstrate that the proposed HEAT consistently outperforms several state-of-the-art baselines.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Balazevic, I., Allen, C., Hospedales, T.M.: Hypernetwork knowledge graph embeddings. In: Proceedings of the ICANN, vol. 11731, pp. 553–565 (2019)
Balazevic, I., Allen, C., Hospedales, T.M.: Tucker: Tensor factorization for knowledge graph completion. In: Proceedings of the EMNLP-IJCNLP, pp. 5184–5193 (2019)
Bordes, A., Usunier, N., Garcia-Duran, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: Proceedings of the NeurIPS, pp. 2787–2795 (2013)
Chami, I., Wolf, A., Juan, D.C., Sala, F., Ravi, S., Re, C.: Low-dimensional hyperbolic knowledge graph embeddings. In: Proceedings of the ACL, pp. 6901–6914 (2020)
Dettmers, T., Minervini, P., Stenetorp, P., Riedel, S.: Convolutional 2d knowledge graph embeddings. In: Proceedings of the AAAI (2018)
Ebisu, T., Ichise, R.: Toruse: Knowledge graph embedding on a lie group. In: AAAI (2018)
Galkin, M., Trivedi, P., Maheshwari, G., Usbeck, R., Lehmann, J.: Message passing for hyper-relational knowledge graphs. In: Proceedings of the 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 ACL, pp. 6141–6151 (2020)
Guan, S., Jin, X., Wang, Y., Cheng, X.: Link prediction on n-ary relational data. In: Proceedings of the WWW, pp. 583–593 (2019)
Hu, Z., Cao, Y., Huang, L., Chua, T.: How knowledge graph and attention help? A qualitative analysis into bag-level relation extraction. In: Proceedings of the ACL/IJCNLP, pp. 4662–4671 (2021)
Kazemi, S.M., Poole, D.: Simple embedding for link prediction in knowledge graphs. In: Proceedings of the NeurIPS, pp. 4284–4295 (2018)
Kingma, D., Jimmy, B.: Adam: A method for stochastic optimization. Comput. Sci. (2014)
Kolyvakis, P., Kalousis, A., Kiritsis, D.: Hyperkg: Hyperbolic knowledge graph embeddings for knowledge base completion. In: arXiv (2019)
Nadgeri, A., et al.: Kgpool: Dynamic knowledge graph context selection for relation extraction. In: Proceedings of the ACL/IJCNLP (Findings), pp. 535–548 (2021)
Naseem, T., et al.: A semantics-aware transformer model of relation linking for knowledge base question answering. In: Proceedings of the ACL/IJCNLP, pp. 256–262 (2021)
Nayyeri, M., Xu, C., Yaghoobzadeh, Y., Yazdi, H.S., Lehmann, J.: Toward understanding the effect of loss function on then performance of knowledge graph embedding. In: arXiv (2019)
Nguyen, D.Q., Nguyen, T.D., Nguyen, D.Q., Phung, D.: A novel embedding model for knowledge base completion based on convolutional neural network. In: Proceedings of the NAACL, pp. 327–333 (2018)
Nickel, Tresp, Kriegel: A three-way model for collective learning on multi-relational data. In: Proceedings of the ICML, pp. 809–816 (2011)
Rosso, P., Yang, D., Cudré-Mauroux, P.: Beyond triplets: Hyper-relational knowledge graph embedding for link prediction. In: Proceedings of the WWW, pp. 1885–1896 (2020)
Schlichtkrull, M., Kipf, T.N., Bloem, P., van den Berg, R., Titov, I., Welling, M.: Modeling relational data with graph convolutional networks. In: Gangemi, A., et al. (eds.) ESWC 2018. LNCS, vol. 10843, pp. 593–607. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-93417-4_38
Sun, Z., Huang, J., Hu, W., Chen, M., Guo, L., Qu, Y.: Transedge: Translating relation-contextualized embeddings for knowledge graphs. In: Proceedings of the ISWC, pp. 612–629 (2019)
Sun, Z., Deng, Z.H., Nie, J.Y., Tang, J.: Rotate: Knowledge graph embedding by relational rotation in complex space. In: Proceedings of the ICLR (2019)
Vashishth, S., Sanyal, S., Nitin, V., Agrawal, N., Talukdar, P.P.: Interacte: Improving convolution-based knowledge graph embeddings by increasing feature interactions. In: Proceedings of the AAAI, pp. 3009–3016 (2020)
Vashishth, S., Sanyal, S., Nitin, V., Talukdar, P.P.: Composition-based multi-relational graph convolutional networks. In: Proceedings of the ICLR (2020)
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 IJCAI, pp. 1300–1307 (2016)
Yang, B., Tau Yih, W., He, X., Gao, J., Deng, L.: Embedding entities and relations for learning and inference in knowledge bases. In: Proceedings of the ICLR (2015)
Yasunaga, M., Ren, H., Bosselut, A., Liang, P., Leskovec, J.: QA-GNN: Reasoning with language models and knowledge graphs for question answering. In: Proceedings of the NAACL-HLT, pp. 535–546 (2021)
Yu, D., Yang, Y.: Improving hyper-relational knowledge graph completion. Arxiv (2021)
Zhang, R., Li, J., Mei, J., Mao, Y.: Scalable instance reconstruction in knowledge bases via relatedness affiliated embedding. In: Proceedings of the WWW, pp. 1185–1194 (2018)
Zhang, W., Paudel, B., Wang, L.: Iteratively learning embeddings and rules for knowledge graph reasoning. In: Proceedings of the WWW, pp. 2366–2377 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ma, T., Huang, L., Xue, H. (2023). Improving Hyper-relational Knowledge Graph Representation with Multi-grained Encoding. In: Wang, X., et al. Database Systems for Advanced Applications. DASFAA 2023. Lecture Notes in Computer Science, vol 13944. Springer, Cham. https://doi.org/10.1007/978-3-031-30672-3_51
Download citation
DOI: https://doi.org/10.1007/978-3-031-30672-3_51
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-30671-6
Online ISBN: 978-3-031-30672-3
eBook Packages: Computer ScienceComputer Science (R0)