Abstract
Recent advances in relational information extraction have allowed to automatically construct large-scale knowledge graphs (KGs). Nevertheless, an automatic process entails that a significant amount of uncertain facts are introduced into KGs. Uncertain knowledge graphs (UKGs) such as NELL and Probase model this kind of uncertainty as confidence scores associated to facts for providing more precise knowledge descriptions. Existing UKG completion methods require sufficient training examples for each relation. However, most relations only have few facts in real-world UKGs. To solve the above problem, in this paper, we propose a novel method to complete few-shot UKGs based on Gaussian metric learning (GMUC) which could complete missing facts and confidence scores with few examples available. By employing a Gaussian-based encoder and metric function, GMUC could effectively capture uncertain semantic information. Extensive experiments conducted over various datasets with different uncertainty levels demonstrate that our method consistently outperforms baselines.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Auer, S., Bizer, C., Kobilarov, G., Lehmann, J., Cyganiak, R., Ives, Z.: DBpedia: a nucleus for a web of open data. In: Aberer, K., et al. (eds.) ASWC/ISWC-2007. LNCS, vol. 4825, pp. 722–735. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-76298-0_52
Bollacker, K.D., Evans, C., Paritosh, P., Sturge, T., Taylor, J.: Freebase: a collaboratively created graph database for structuring human knowledge. In: Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data, SIGMOD 2008, pp. 1247–1250 (2008)
Bordes, A., Usunier, N., García-Durán, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: Proceedings of the 2013 Annual Conference on Neural Information Processing Systems, NeurIPS 2013, pp. 2787–2795 (2013)
Carlson, A., Betteridge, J., Kisiel, B., Settles, B., Jr., E.R.H., Mitchell, T.M.: Toward an architecture for never-ending language learning. In: Proceedings of the 2010 AAAI Conference on Artificial Intelligence, AAAI 2010 (2010)
Chen, M., Zhang, W., Zhang, W., Chen, Q., Chen, H.: Meta relational learning for few-shot link prediction in knowledge graphs. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing, EMNLP 2019, pp. 4216–4225 (2019)
Chen, X., Chen, M., Shi, W., Sun, Y., Zaniolo, C.: Embedding uncertain knowledge graphs. In: Proceedings of the 2019 AAAI Conference on Artificial Intelligence, AAAI 2019, pp. 3363–3370 (2019)
Dettmers, T., Minervini, P., Stenetorp, P., Riedel, S.: Convolutional 2d knowledge graph embeddings. In: Proceedings of the 2018 AAAI Conference on Artificial Intelligence, AAAI 2018, pp. 1811–1818 (2018)
Du, Z., Zhou, C., Ding, M., Yang, H., Tang, J.: Cognitive knowledge graph reasoning for one-shot relational learning. CoRR (2019)
Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: Proceedings of the 2017 International Conference on Machine Learning, ICML 2017, vol. 70, pp. 1126–1135 (2017)
He, S., Liu, K., Ji, G., Zhao, J.: Learning to represent knowledge graphs with Gaussian embedding. In: Proceedings of the 2015 ACM International Conference on Information and Knowledge Management, CIKM 2015, pp. 623–632 (2015)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9, 1735–1780 (1997)
Huang, Z., Iyer, R.G., Xiao, Z.: Uncertain knowledge graph embedding using probabilistic logic neural networks (2017)
Kertkeidkachorn, N., Liu, X., Ichise, R.: GTransE: generalizing translation-based model on uncertain knowledge graph embedding. In: Ohsawa, Y., et al. (eds.) JSAI 2019. AISC, vol. 1128, pp. 170–178. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-39878-1_16
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) Proceedings of the 2015 International Conference on Learning Representations, ICLR 2015 (2015)
Koch, G., Zemel, R., Salakhutdinov, R.: Siamese neural networks for one-shot image recognition. In: Proceedings of the 2015 Workshop on International Conference on Machine Learning, ICML 2015, vol. 2 (2015)
Li, Z., Zhou, F., Chen, F., Li, H.: Meta-SGD: Learning to learn quickly for few shot learning. CoRR abs/1707.09835 (2017)
Munkhdalai, T., Yu, H.: Meta networks. Proc. Mach. Learn. Res. 70, 2554 (2017)
Nickel, M., Tresp, V., Kriegel, H.: A three-way model for collective learning on multi-relational data. In: Proceedings of the 2011 International Conference on Machine Learning, ICML 2011, pp. 809–816 (2011)
Qi, G., Gao, H., Wu, T.: The research advances of knowledge graph. Technol. Intell. Eng. 3, 4–25 (2017)
Ravi, S., Larochelle, H.: Optimization as a model for few-shot learning. In: Proceedings of the 2017 International Conference on Learning Representations, ICLR 2017 (2017)
Snell, J., Swersky, K., Zemel, R.S.: Prototypical networks for few-shot learning. In: Proceedings of the 2017 Annual Conference on Neural Information Processing Systems, NeurIPS 2017, pp. 4077–4087 (2017)
Socher, R., Chen, D., Manning, C.D., Ng, A.Y.: Reasoning with neural tensor networks for knowledge base completion. In: Proceedings of the 2013 Annual Conference on Neural Information Processing Systems, NeurIPS 2013, pp. 926–934 (2013)
Sosa, D.N., Derry, A., Guo, M., Wei, E., Brinton, C., Altman, R.B.: A literature-based knowledge graph embedding method for identifying drug repurposing opportunities in rare diseases. bioRxiv, p. 727925 (2019)
Speer, R., Chin, J., Havasi, C.: ConceptNet 5.5: an open multilingual graph of general knowledge. In: Proceedings of the 2017 AAAI Conference on Artificial Intelligence, AAAI 2017, pp. 4444–4451 (2017)
Trouillon, T., Welbl, J., Riedel, S., Gaussier, É., Bouchard, G.: Complex embeddings for simple link prediction. In: Proceedings of the 2016 International Conference on Machine Learning, ICML 2016, pp. 2071–2080 (2016)
Vilnis, L., McCallum, A.: Word representations via gaussian embedding. In: Bengio, Y., LeCun, Y. (eds.) Proceedings of the 2015 International Conference on Learning Representations, ICLR 2015 (2015)
Vinyals, O., Blundell, C., Lillicrap, T., Kavukcuoglu, K., Wierstra, D.: Matching networks for one shot learning. In: Proceedings of the 2016 Annual Conference on Neural Information Processing Systems, NeurIPS 2016, pp. 3630–3638 (2016)
Vrandečić, D., Krötzsch, M.: Wikidata: a free collaborative knowledgebase. Commun. ACM 57, 78–85 (2014)
Xie, R., Liu, Z., Lin, F., Lin, L.: Does William Shakespeare REALLY Write Hamlet? knowledge representation learning with confidence. In: Proceedings of the 2018 AAAI Conference on Artificial Intelligence, AAAI 2018, pp. 4954–4961 (2018)
Xiong, W., Yu, M., Chang, S., Wang, W.Y., Guo, X.: One-shot relational learning for knowledge graphs. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, EMNLP 2018, pp. 1980–1990 (2018)
Yang, B., Yih, W., He, X., Gao, J., Deng, L.: Embedding entities and relations for learning and inference in knowledge bases. In: Proceedings of the 2015 International Conference on Learning Representations, ICLR 2015 (2015)
Yu, M., et al.: Diverse few-shot text classification with multiple metrics. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2018, pp. 1206–1215 (2018)
Zhang, C., Yao, H., Huang, C., Jiang, M., Li, Z., Chawla, N.V.: Few-shot knowledge graph completion. In: Proceedings of the 2020 AAAI Conference on Artificial Intelligence, AAAI 2020, pp. 3041–3048 (2020)
Acknowledgements
This work was partially supported by the National Key Research and Development Program of China under grants (2018YFC0830200, 2017YFB1002801), the National Natural Science Foundation of China grants (U1736204, 62006040), and the Judicial Big Data Research Centre, School of Law at Southeast University. In addition, we wish to thank Prof. Qiu Ji for her valuable suggestion.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, J., Wu, T., Qi, G. (2021). Gaussian Metric Learning for Few-Shot Uncertain Knowledge Graph Completion. In: Jensen, C.S., et al. Database Systems for Advanced Applications. DASFAA 2021. Lecture Notes in Computer Science(), vol 12681. Springer, Cham. https://doi.org/10.1007/978-3-030-73194-6_18
Download citation
DOI: https://doi.org/10.1007/978-3-030-73194-6_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-73193-9
Online ISBN: 978-3-030-73194-6
eBook Packages: Computer ScienceComputer Science (R0)