Abstract
We investigate the problem of learning continuous vector representations of knowledge graphs for predicting missing links. Recent results suggest that using a Hermitian inner product on complex-valued embeddings or convolutions on real-valued embeddings can be effective means for predicting missing links. We bring these insights together and propose ConEx—a multiplicative composition of a 2D convolution with a Hermitian inner product on complex-valued embeddings. ConEx utilizes the Hadamard product to compose a 2D convolution followed by an affine transformation with a Hermitian inner product in \(\mathbb {C}\). This combination endows ConEx with the capability of (1) controlling the impact of the convolution on the Hermitian inner product of embeddings, and (2) degenerating into ComplEx if such a degeneration is necessary to further minimize the incurred training loss. We evaluated our approach on five of the most commonly used benchmark datasets. Our experimental results suggest that ConEx outperforms state-of-the-art models on four of the five datasets w.r.t. Hits@1 and MRR even without extensive hyperparameter optimization. Our results also indicate that the generalization performance of state-of-the-art models can be further increased by applying ensemble learning. We provide an open-source implementation of our approach, including training and evaluation scripts as well as pretrained models (github.com/dice-group/Convolutional-Complex-Knowledge-Graph-Embeddings).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
References
Allen, C., Balazevic, I., Hospedales, T.: Interpreting knowledge graph relation representation from word embeddings. In: International Conference on Learning Representations (2021). https://openreview.net/forum?id=gLWj29369lW
Balažević, I., Allen, C., Hospedales, T.: Multi-relational poincaré graph embeddings. In: Advances in Neural Information Processing Systems, pp. 4465–4475 (2019)
Balažević, I., Allen, C., Hospedales, T.M.: Hypernetwork knowledge graph embeddings. In: Tetko, I.V., Kůrková, V., Karpov, P., Theis, F. (eds.) ICANN 2019. LNCS, vol. 11731, pp. 553–565. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-30493-5_52
Balažević, I., Allen, C., Hospedales, T.M.: Tucker: tensor factorization for knowledge graph completion. arXiv preprint arXiv:1901.09590 (2019)
Cai, H., Zheng, V.W., Chang, K.C.C.: A comprehensive survey of graph embedding: problems, techniques, and applications. IEEE Trans. Knowl. Data Eng. 30(9), 1616–1637 (2018)
Chen, H., Wang, W., Li, G., Shi, Y.: A quaternion-embedded capsule network model for knowledge graph completion. IEEE Access 8, 100890–100904 (2020)
Demir, C., Moussallem, D., Ngomo, A.-C.N.: A shallow neural model for relation prediction. arXiv preprint arXiv:2101.09090 (2021)
Demir, C., Ngomo, A.-C.N.: A physical embedding model for knowledge graphs. In: Wang, X., Lisi, F.A., Xiao, G., Botoeva, E. (eds.) JIST 2019. LNCS, vol. 12032, pp. 192–209. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-41407-8_13
Dettmers, T., Minervini, P., Stenetorp, P., Riedel, S.: Convolutional 2d knowledge graph embeddings. In: 32nd AAAI Conference on Artificial Intelligence (2018)
Eder, J.S.: Knowledge graph based search system. US Patent App. US13/404,109 (21 June 2012)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Hogan, A., et al.: Knowledge graphs. arXiv preprint arXiv:2003.02320 (2020)
Huang, X., Zhang, J., Li, D., Li, P.: Knowledge graph embedding based question answering. In: Proceedings of the 12th ACM International Conference on Web Search and Data Mining, pp. 105–113 (2019)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)
Ji, S., Pan, S., Cambria, E., Marttinen, P., Yu, P.S.: A survey on knowledge graphs: representation, acquisition and applications. arXiv preprint arXiv:2002.00388 (2020)
Joulin, A., Grave, E., Bojanowski, P., Nickel, M., Mikolov, T.: Fast linear model for knowledge graph embeddings. arXiv preprint arXiv:1710.10881 (2017)
Kazemi, S.M., Poole, D.: Simple embedding for link prediction in knowledge graphs. In: Advances in Neural Information Processing Systems, pp. 4284–4295 (2018)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60(6), 84–90 (2017)
Krompaß, D., Baier, S., Tresp, V.: Type-constrained representation learning in knowledge graphs. In: Arenas, M., et al. (eds.) ISWC 2015. LNCS, vol. 9366, pp. 640–655. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-25007-6_37
Malyshev, S., Krötzsch, M., González, L., Gonsior, J., Bielefeldt, A.: Getting the most out of Wikidata: semantic technology usage in Wikipedia’s knowledge graph. In: Vrandečić, D., et al. (eds.) ISWC 2018. LNCS, vol. 11137, pp. 376–394. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00668-6_23
Murphy, K.P.: Machine Learning: A Probabilistic Perspective. MIT Press (2012)
Nguyen, D.Q., Nguyen, T.D., Nguyen, D.Q., Phung, D.: A novel embedding model for knowledge base completion based on convolutional neural network. arXiv preprint arXiv:1712.02121 (2017)
Nickel, M., Murphy, K., Tresp, V., Gabrilovich, E.: A review of relational machine learning for knowledge graphs. Proc. IEEE 104(1), 11–33 (2015)
Nickel, M., Rosasco, L., Poggio, T.: Holographic embeddings of knowledge graphs. arXiv preprint arXiv:1510.04935 (2015)
Nickel, M., Tresp, V., Kriegel, H.P.: A three-way model for collective learning on multi-relational data. In: ICML, vol. 11, pp. 809–816 (2011)
Qin, C., et al.: A survey on knowledge graph based recommender systems. Scientia Sinica Informationis 50, 937 (2020)
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)
Saleem, M., Kamdar, M.R., Iqbal, A., Sampath, S., Deus, H.F., Ngonga Ngomo, A-.C.: Big linked cancer data: integrating linked TCGA and PubMed. J. Web Semant. 27, 34–41 (2014)
Strubell, E., Ganesh, A., McCallum, A.: Energy and policy considerations for deep learning in NLP. arXiv preprint arXiv:1906.02243 (2019)
Sun, Z., Deng, Z.H., Nie, J.Y., Tang, J.: RotatE: knowledge graph embedding by relational rotation in complex space. arXiv preprint arXiv:1902.10197 (2019)
Tieleman, T., Hinton, G.: Lecture 6.5-rmsprop: divide the gradient by a running average of its recent magnitude. COURSERA: Neural Netw. Mach. Learn. 4(2), 26–31 (2012)
Trouillon, T., Dance, C.R., Gaussier, É., Welbl, J., Riedel, S., Bouchard, G.: Knowledge graph completion via complex tensor factorization. J. Mach. Learn. Res. 18(1), 4735–4772 (2017)
Trouillon, T., Nickel, M.: Complex and holographic embeddings of knowledge graphs: a comparison. arXiv preprint arXiv:1707.01475 (2017)
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 (2016)
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)
Yang, B., Yih, W., He, X., Gao, J., Deng, L.: Embedding entities and relations for learning and inference in knowledge bases. In: ICLR (2015)
Zhang, S., Tay, Y., Yao, L., Liu, Q.: Quaternion knowledge graph embeddings. In: Advances in Neural Information Processing Systems, pp. 2731–2741 (2019)
Acknowledgments
This work has been supported by the BMWi-funded project RAKI (01MD19012D) as well as the BMBF-funded project DAIKIRI (01IS19085B). We are grateful to Diego Moussallem for valuable comments on earlier drafts and to Pamela Heidi Douglas for editing the manuscript.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix
Appendix
Statistical Hypothesis Testing. We carried out a Wilcoxon signed-rank test to check whether our results are significant. Our null hypothesis was that the link prediction performances of ConEx, ComplEx and ConvE come from the same distribution. The alternative hypothesis was correspondingly that these results come from different distributions. To perform the Wilcoxon signed-rank test (two-sided), we used the differences of the MRR, Hits@1, Hits@3, and Hits@10 performances on WN18RR, FB15K-237 and YAGO3-10. We performed two hypothesis tests between ConEx and ComplEx as well as between ConEx and ConvE. In both tests, we were able to reject the null hypothesis with a p-value \(< 1\%\). Ergo, the superior performance of ConEx is statistically significant.
Ablation Study. We conducted our ablation study in a fashion akin to [9]. Like [9], we evaluated 2 different parameter initialisations to compute confidence intervals that is defined as \(\bar{x}\pm 1.96 \cdot \frac{s}{\sqrt{n}}\), where \(\bar{x}= \frac{1}{n} \sum _i ^n x_i\) and \(s=\sqrt{\frac{\sum _i ^n (x_i - \bar{x} )^2}{n}}\), respectively. Hence, the mean and the standard deviation are computed without Bessel’s correction. Our results suggest that the initialization of parameters does not play a significant role in the link performance of ConEx. The dropout technique is the most important component in the generalization performance of ConEx. This is also observed in [9]. Moreover, replacing the Adam optimizer with the RMSprop optimizer [32] leads to slight increases in the variance of the link prediction results. During our ablation experiments, we were also interested in decomposing ConEx through removing \(\text {conv}(\cdot ,\cdot )\), after ConEx is trained with it on benchmark datasets. By doing so, we aim to observe the impact of a 2D convolution in the computation of scores. Table 9 indicates that the impact of \(\text {conv}(\cdot ,\cdot )\) differs depending on the input knowledge graph. As the size of the input knowledge graph increases, the impact of \(\text {conv}(\cdot ,\cdot )\) on the computation of scores of triples increases.
Link Prediction Results on WN18 and FB15K. Table 10 reports link prediction results on the WN18 and FB15K benchmark datasets.
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Demir, C., Ngomo, AC.N. (2021). Convolutional Complex Knowledge Graph Embeddings. In: Verborgh, R., et al. The Semantic Web. ESWC 2021. Lecture Notes in Computer Science(), vol 12731. Springer, Cham. https://doi.org/10.1007/978-3-030-77385-4_24
Download citation
DOI: https://doi.org/10.1007/978-3-030-77385-4_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-77384-7
Online ISBN: 978-3-030-77385-4
eBook Packages: Computer ScienceComputer Science (R0)