Abstract
Inductive relation prediction is to predict relations between unseen entities. The current methods implicitly learn the logical rules in the knowledge graph through the local subgraph structures, and obtain the latent semantic representation of the predicted triples. However, existing methods lack relation information of neighboring triples due to the incompleteness of the knowledge graph, and the representation of entities does not consider the connection structures between relations which contain different semantic information. To address these challenges, we propose a novel entity representation by Neighboring Relations Topology Graph (NRTG) for inductive relation prediction. Specifically, we divide connection structures between relations into several topological patterns, and design a module to extract relations of all neighboring triples for constructing Neighboring Relations Topology Graph (NRTG). In NRTG, the nodes represent the relations and the edges represent the topological patterns. Afterward, we design an information aggregation module to encode the NRTG as the entity representation, and then use the scoring network to predict relations between unseen entities. Experiments demonstrate that our model can effectively capture relation information of neighboring triples and semantic information of connection structures between relations. Moreover, it outperforms existing methods on benchmark datasets for the inductive relation prediction task.
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
Bordes, A., et al.: Translating embeddings for modeling multi-relational data. In: Advances in Neural Information Processing Systems 26 (2013)
Chen, J., et al.: Topology-aware correlations between relations for inductive link prediction in knowledge graphs. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35. 7, pp. 6271–6278 (2021)
Dettmers, T., et al.: Convolutional 2d knowledge graph embeddings. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32, January 2018
Galárraga, L.A., et al.: AMIE: association rule mining under in-complete evidence in ontological knowledge bases. In: Proceedings of the 22nd international conference on World Wide Web, pp. 413–422 (2013)
Gilmer, J., et al.: Neural message passing for quantum chemistry. In: International Conference on Machine Learning. PMLR. 2017, pp. 1263–1272
Hamaguchi, T., et al.: Knowledge transfer for out-of-knowledge-base entities: a graph neural network approach. In: ar**v preprint ar**v:1706.05674 (2017)
Hamilton, W.L., Ying, R., Leskovec, J.: Representation learning on graphs: methods and applications. In: ar**v preprint ar**v:1709.05584 (2017)
Huang, X., et al.: Knowledge graph embedding based question answering. In: Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, pp. 105–113 (2019)
Kingma, D.P., Ba, J.: Adam: a method for stochastic op- timization. In: ar**v preprint ar**v:1412.6980 (2014)
Meilicke, C., et al.: Fine-grained evaluation of rule-and embedding-based systems for knowledge graph completion. In: International Semantic Web Conference, pp. 3–20. Springer (2018)
Nathani, D., et al.: Learning attention-based embeddings for relation prediction in knowledge graphs. In: ar**v preprint ar**v:1906.01195 (2019)
Nguyen, D.Q., et al.: A novel embedding model for knowledge base completion based on convolutional neural network. In: ar**v preprint ar**v:1712.02121 (2017)
Sadeghian, A., et al.: Drum: end-to-end di erentiable rule mining on knowledge graphs. In: Advances in Neural Information Processing Systems 32 (2019)
Scarselli, F., et al.: The graph neural network model. IEEE Trans. Neural Networks 20(1), 61–80 (2008)
Schlichtkrull, M., et al.: Modeling relational data with graph convolutional networks. In: European Semantic Web Conference, pp. 593–607. Springer (2018)
Sun, Z., et al.: Rotate: knowledge graph embedding by relational rotation in complex space. In: ar**v preprint ar**v:1902.10197 (2019)
Teru, K., Denis, E., Hamilton, W.: Inductive relation pre- diction by subgraph reasoning. In: International Conference on Machine Learning. PMLR, pp. 9448–9457 (2020)
Toutanova, K., et al.: Representing text for joint embedding of text and knowledge bases. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 1499–1509 (2015)
Tran, H.D., et al.: Towards nonmonotonic relational learning from knowledge graphs. In: International Conference on Inductive Logic Pro- gramming, pp. 94–107. Springer (2016)
Trouillon, T., et al.: Knowledge graph completion via complex tensor factorization. In: ar**v preprint ar**v:1702.06879 (2017)
Wang, H., et al.: Ripplenet: propagating user preferences on the knowledge graph for recommender systems. In: Proceedings of the 27th ACM International Conference on Information and Knowledge Management, pp. 417–426 (2018)
**ong, W., Hoang, T., Wang, Y.: Deeppath: a reinforcement learning method for knowledge graph reasoning. In: ar**v preprint ar**v:1707.06690 (2017)
Yang, F., Yang, Z., Cohen, W.W.: Di erentiable learning of logical rules for knowledge base reasoning. In: Advances in Neural Information Processing Systems 30 (2017)
Yu, H., Lu, J., Zhang, G.: Online topology learning by a gaussian membership-based self-organizing incremental neural network. In: IEEE Trans. Neural Networks Learn. Syst. 31(10), 3947–3961 (2019)
Yu, H., Lu, J., Zhang, G.: Topology learning-based Fuzzy random neural network for streaming data regression. IEEE Trans, Fuzzy Syst (2020)
Zhang, Z., et al.: Relational graph neural network with hierarchical at- tention for knowledge graph completion. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34(05), 9612–9619 (2020)
Zhang, Z., et al.: ERNIE: enhanced language representation with informative entities. In: ar**v preprint ar**v:1905.07129 (2019)
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
Chen, Z., Yu, H., Li, J., Luo, X. (2022). Entity Representation by Neighboring Relations Topology for Inductive Relation Prediction. In: Khanna, S., Cao, J., Bai, Q., Xu, G. (eds) PRICAI 2022: Trends in Artificial Intelligence. PRICAI 2022. Lecture Notes in Computer Science, vol 13630. Springer, Cham. https://doi.org/10.1007/978-3-031-20865-2_5
Download citation
DOI: https://doi.org/10.1007/978-3-031-20865-2_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20864-5
Online ISBN: 978-3-031-20865-2
eBook Packages: Computer ScienceComputer Science (R0)