Abstract
Knowledge hypergraph link prediction aims to predict missing relationships in knowledge hypergraphs and is one of the effective methods for graph completion. The existing optimal knowledge hypergraph link method based on tensor decomposition, i.e., GETD (Generalized Model based on Tucker Decomposition and Tensor Ring Decomposition), has achieved good performance by extending Tucker decomposition, but there are still two main problems: (1)GETD does not establish operations or connections between any two tensor factors, resulting in limited representation of tensor correlation (referred to as finiteness); (2)The tensor decomposed by GETD is highly sensitive to the arrangement of tensor patterns (referred to as sensitivity). In response to the above issues, we propose a knowledge hypergraph link prediction model, called GETD\(^+\), based on fully-connected tensor decomposition(FCTN). By combining Tucker decomposition and FCTN, a multi-linear operation/connection is established for any two factor tensors obtained from tensor decomposition. This not only enhances the representation ability of tensors, but also eliminates sensitivity to tensor pattern arrangement. Finally, the superiority of the GETD\(^+\) model was verified through a large number of experiments on real knowledge hypergraph datasets and knowledge graph datasets.
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
Wen, J.F., Li, J.X., Mao, Y.Y., et al.: On the representation and embedding of knowledge bases beyond binary relations. In: Twenty-Fifth International Joint Conference on Artificial Intelligence (IJCAI), pp. 1300–1307 (2016)
Almousa, M., Benlamri, R., Khoury, R.: A novel word sense disambiguation approach using wordnet knowledge graph. arXiv preprint arXiv:2101.02875 (2021)
Dai, Z., Li, L., Xu, W.: CFO: conditional focused neural question answering with largescale knowledge bases. In: 54th Annual Meeting of the Association for Computational Linguistics (ACL), pp. 800–810 (2016)
Chen, Y., Wu, L., Zaki, M.J.: Bidirectional attentive memory networks for question answering over knowledge bases. In: ACL, pp. 2913–2923 (2019)
Ji, S., Feng, Y., Ji, R., et al.: Dual channel hypergraph collaborative filtering. In: 26th ACM International Conference on Knowledge Discovery and Data Mining (SIGKDD), pp. 2020–2029 (2020)
Yu, W., Qin, Z.: Graph convolutional network for recommendation with low-pass collaborative filters. In: International Conference on Machine Learning (ICML), pp. 10936–10945 (2020)
Liu, Y., Yao, Q.M., Li, Y.: Generalizing tensor decomposition for N-ary relational knowledge bases. In: 29th International World Wide Web Conferences (WWW), pp. 1104–1114 (2020)
Balaevi, I., Allen, C., Hospedales, T.M.: TuckER: tensor factorization for knowledge graph completion. In: ICML, pp. 5184–5193 (2019)
Zhao, QB., Zhou, G.X., Xie, S.L., et al.: Tensor ring decomposition. arXiv preprint arXiv:1606.05535 (2016)
Zheng, Y.B., Huang, T.Z., Zhao, X.L., et al.: Fully-connected tensor network decomposition and its application to higher-order tensor completion. In: AAAI, vol. 35(12), pp. 11071–11078 (2021)
Bordes, A., Usunier, N., Garcia-Duran, A., et al.: Translating embeddings for modeling multi-relational data. In: 27th Annual Conference on Neural Information Processing Systems (NIPS), pp. 2787–2795 (2013)
Zhang, R.C., Li, J.P., Mei, J.J., et al.: Scalable instance reconstruction in knowledge bases via relatedness affiliated embedding. In: WWW, pp. 1185–1194 (2018)
Guan, S.P., Jin, X.L., Wang, Y.Z., et al.: Link prediction on N-ary relational data. In: WWW, pp. 583–593 (2019)
Kazemi, S.M., Poole, D.: Simple embedding for link prediction in knowledge graphs. In: NIPS, pp. 4289–4300 (2018)
Trouillon, T., Welbl, J., Riedel, S., et al.: Complex embeddings for simple link prediction. In: ICML, pp. 2071–2080 (2016)
Guan, S.P., Jin, X.L., Guo, J.F., et al.: Link prediction on n-ary relational data based on relatedness evaluation. IEEE Trans. Knowl. Data Eng. (TKDE) 35(1), 672–685 (2023)
Nguyen, D.Q., Nguyen, T.D., Dat, Q.N., et al.: A novel embedding model for knowledge base completion based on convolutional neural network. In: ACL, pp. 327–333 (2018)
Dettmers, T., Minervini, P., Stenetorp, P., et al.: Convolutional 2D knowledge graph embeddings. In: AAAI, pp. 1811–1818 (2018)
Chen, Z., Wang, X., Wang, C., et al.: Explainable link prediction in knowledge hypergraphs. In: 31st ACM International Conference on Information and Knowledge Management (CIKM), pp. 262–271 (2020)
Gao, Y., Tian, X., Zhou, J., et al.: Knowledge graph embedding based on quaternion transformation and convolutional neural network. In: 17th International Conference on Advanced Data Mining and Applications (ADMA), pp. 128–136 (2021)
Hou, R., Zhu, W., Zhu, C.: Global relation auxiliary graph attention network for knowledge graph completion. In: 5th International Conference on Artificial Intelligence and Big Data (ICAIBD), pp. 532–538 (2022)
Xu, Y.W., Zhang, H.J., Cheng, K., et al.: Knowledge graph embedding with entity attributes using hypergraph neural networks. Intell. Data Anal. 26(4), 959–975 (2022)
Bordes, A., Glorot, X., Weston, J., Bengio, Y.: A semantic matching energy function for learning with multi-relational data. Mach. Learn. 94(2), 233–259 (2013). https://doi.org/10.1007/s10994-013-5363-6
Antoine, B., Nicolas, U., Alberto, G.D., et al.: Irreflexive and hierarchical relations as translations. arXiv preprint arXiv:1304.7158 (2013)
Yang, B.S., Yih, W.T., He, X.D., et al.: Embedding entities and relations for learning and inference in knowledge bases. In: International Conference on Learning Representations (ICLR) (2015)
Acknowledgment
The work is supported by the National Natural Science Foundation of China (No.62372342, No. 61702381).
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
Pang, J., Qin, HC., Liu, Y., Liu, XQ. (2023). Two Birds with One Stone: A Link Prediction Model for Knowledge Hypergraph Based on Fully-Connected Tensor Decomposition. In: Yang, X., et al. Advanced Data Mining and Applications. ADMA 2023. Lecture Notes in Computer Science(), vol 14177. Springer, Cham. https://doi.org/10.1007/978-3-031-46664-9_6
Download citation
DOI: https://doi.org/10.1007/978-3-031-46664-9_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-46663-2
Online ISBN: 978-3-031-46664-9
eBook Packages: Computer ScienceComputer Science (R0)