Abstract
Knowledge graph (KG) embedding methods learn the low dimensional vector representations of entities and relations of a knowledge graph, facilitating the link prediction task in knowledge graphs. During learning of embeddings, sampling negative triples is important because KGs have only observed positive triples. To the best of our knowledge, uniform-random, generative adversarial network (GAN)-based, and NSCaching, structure aware negative sampling (SANS) are four negative sampling methods in the literature. Unfortunately, they suffer from computational and memory inefficiency problems. In addition, their prediction performance are affected by the ‘vanishing gradient’ problem because of poor quality of sampled negative triples. In this paper, we propose a simple negative sampling (SNS) method based on the assumption that the entities which are closer in the embedding space to the corrupted entity are able to provide high-quality negative triples. Furthermore SNS has a good exploitation potential as it uses sampled high-quality negatives for improving the quality of negative triples in next steps. We evaluate our sampling method through link prediction task on five well-known knowledge graph datasets, WN18, WN18RR, FB15K, FB15K-237, YAGO3-10. The method is also evaluated on a new biological KG dataset (FIGHT-HF-23R). Experimental results show that the SNS improves the prediction performance of KG embedding models, and outperforms the existing sampling methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Paulheim, H.: Knowledge graph refinement: a survey of approaches and evaluation methods. Semant. Web 8(3), 489–508 (2017)
Dong, X., et al.: Knowledge vault: a web-scale approach to probabilistic knowledge fusion. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 601–610 (2014)
Cai, L., Wang, W.Y.: KBGAN: adversarial learning for knowledge graph embeddings. In: 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 1470–1480 (2018)
Zhang, Y., Yao, Q., Shao, Y., Chen, L.: NSCaching: simple and efficient negative sampling for knowledge graph embedding. In: 2019 IEEE 35th International Conference on Data Engineering, pp. 614–625 (2019)
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)
Bordes, A., Usunier, N., Garcia-Duran, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: Advances in Neural Information Processing Systems, vol. 26, pp. 1–9 (2013)
Hu, K., Liu, H., Hao, T.: A knowledge selective adversarial network for link prediction in knowledge graph. In: Tang, J., Kan, MY., Zhao, D., Li, S., Zan, H. (eds.) CCF International Conference on Natural Language Processing and Chinese Computing. LNCS, vol. 11838, pp. 171–183. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32233-5_14
Wang, P., Li, S., Pan, R.: Incorporating GAN for negative sampling in knowledge representation learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)
Ahrabian, K., Feizi, A., Salehi, Y., Hamilton, W.L., Bose, A.J.: Structure aware negative sampling in knowledge graphs. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pp. 6093–6101 (2020)
Chen, J., Xin, B., Peng, Z., Dou, L., Zhang, J.: Optimal contraction theorem for exploration-exploitation tradeoff in search and optimization. IEEE Trans. Syst. Man Cybern. Part A Syst. Hum. 39(3), 680–691 (2009)
Wang, Z., Zhang, J., Feng, J., Chen, Z.: Knowledge graph embedding by translating on hyperplanes. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 28, no. 1, pp. 1112–1119 (2014)
Yang, B., Yih, W.T., He, X., Gao, J., Deng, L.: Embedding entities and relations for learning and inference in knowledge bases. In: International Conference Learning Representation (2014)
Bresso, E., et al.: A data science approach for exploring differential expression profiles of genes in transcriptomic studies-application to the understanding of ageing in obese and lean rats in the FIGHT-HF project. In: JOBIM 2018-Journées Ouvertes Biologie, Informatique et Mathématiques (2018)
Wang, M., Qiu, L., Wang, X.: A survey on knowledge graph embeddings for link prediction. Symmetry 13(3), 485 (2021)
Rossi, A., Matinata, A.: Knowledge graph embeddings: are relation-learning models learning relations? In: EDBT/ICDT Workshops (2020)
Ji, G., He, S., Xu, L., Liu, K., Zhao, J.: Knowledge graph embedding via dynamic mapping matrix. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, vol. 1, pp. 687–696 (2015)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representation (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Islam, M.K., Aridhi, S., Smail-Tabbone, M. (2022). Simple Negative Sampling for Link Prediction in Knowledge Graphs. In: Benito, R.M., Cherifi, C., Cherifi, H., Moro, E., Rocha, L.M., Sales-Pardo, M. (eds) Complex Networks & Their Applications X. COMPLEX NETWORKS 2021. Studies in Computational Intelligence, vol 1073. Springer, Cham. https://doi.org/10.1007/978-3-030-93413-2_46
Download citation
DOI: https://doi.org/10.1007/978-3-030-93413-2_46
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-93412-5
Online ISBN: 978-3-030-93413-2
eBook Packages: EngineeringEngineering (R0)