Abstract
Entity alignment (EA) is to match entities referring to identical real-world facts among different knowledge graphs (KGs). For simplicity, most previous work ignores the existence of dangling entities in the source KG. However, entity alignment task with dangling entities has emerged as a novel demand in real scenarios. Some work explores new dangling-aware loss functions and transfers existing methods on dangling settings, whose performance is still not satisfactory. Thus, in this work, we propose Relation-aware Masked Graph Convolutional Networks (RMGCN). In the learning stage, it can not only take advantage of the masking mechanism to alleviate the negative impact from nearby dangling neighbors, but also take both graph structure and relations of KGs into consideration. In the inference stage, it performs a two-step alignment which firstly filters out dangling entities, and then align the remaining entities. We adopt a novel distribution-based dangling entity detection method in first step to decrease the error propagation from dangling detection to the following EA task. The experimental results show that our model outperforms all state-of-the-art models with at least 7.5% on F1 score.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
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 (2013)
Bruna, J., Zaremba, W., Szlam, A., LeCun, Y.: Spectral networks and deep locally connected networks on graphs. In: 2nd International Conference on Learning Representations, ICLR 2014
Chen, M., Tian, Y., Yang, M., Zaniolo, C.: Multilingual knowledge graph embeddings for cross-lingual knowledge alignment. arXiv preprint arXiv:1611.03954 (2016)
Chen, M., Zhou, T., Zhou, P., Zaniolo, C.: Multi-graph affinity embeddings for multilingual knowledge graphs. In: AKBC@ NIPS (2017)
Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp. 249–256 (2010)
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, pp. 687–696 (2015)
Lehmann, J., et al.: DBpedia-a large-scale, multilingual knowledge base extracted from wikipedia. Semantic Web 6, 167–195 (2015)
Liu, F., Chen, M., Roth, D., Collier, N.: Visual pivoting for (unsupervised) entity alignment. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 4257–4266 (2021)
Liu, J., et al.: Dangling-aware entity alignment with mixed high-order proximities. In: NAACL, pp. 1172–1184 (2022)
Luo, S., Yu, S.: An accurate unsupervised method for joint entity alignment and dangling entity detection. In: ACL, pp. 2330–2339 (2022)
Radovanovic, M., Nanopoulos, A., Ivanovic, M.: Hubs in space: popular nearest neighbors in high-dimensional data. J. Mach. Learn. Res. 11, 2487–2531 (2010)
Sun, Z., Chen, M., Hu, W.: Knowing the no-match: entity alignment with dangling cases. In: ACL-IJCNLP, pp. 3582–3593 (2021)
Sun, Z., Hu, W., Li, C.: Cross-lingual entity alignment via joint attribute-preserving embedding. In: Proceedings of 16th International Semantic Web Conference, pp. 628–644 (2017)
Sun, Z., et al.: Knowledge graph alignment network with gated multi-hop neighborhood aggregation. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 222–229 (2020)
Trisedya, B.D., Qi, J., Zhang, R.: Entity alignment between knowledge graphs using attribute embeddings. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 297–304 (2019)
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 (2014)
Wang, Z., Lv, Q., Lan, X., Zhang, Y.: Cross-lingual knowledge graph alignment via graph convolutional networks. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 349–357 (2018)
Wu, Y., Liu, X., Feng, Y., Wang, Z., Yan, R., Zhao, D.: Relation-aware entity alignment for heterogeneous knowledge graphs. arXiv preprint arXiv:1908.08210 (2019)
Xu, K., et al.: Cross-lingual knowledge graph alignment via graph matching neural network. In: Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics (ACL) (2019)
Yang, H.W., Zou, Y., Shi, P., Lu, W., Lin, J., Sun, X.: Aligning cross-lingual entities with multi-aspect information. In: EMNLP-IJCNLP, pp. 4431–4441 (2019)
Zhang, Q., Sun, Z., Hu, W., Chen, M., Guo, L., Qu, Y.: Multi-view knowledge graph embedding for entity alignment. arXiv preprint arXiv:1906.02390 (2019)
Zhu, R., Luo, X., Ma, M., Wang, P.: Adaptive graph convolutional network for knowledge graph entity alignment. In: EMNLP 2022, pp. 6011–6021 (2022)
Zhu, R., Ma, M., Wang, P.: RAGA: relation-aware graph attention networks for global entity alignment. In: Proceedings of Advances in Knowledge Discovery and Data Mining: 25th Pacific-Asia Conference, PAKDD 2021, pp. 501–513 (2021)
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
Liu, X., Zhou, F., Li, X.Y. (2023). RMGCN: Masked Graph Convolutional Networks for Relation-Aware Entity Alignment with Dangling Cases. In: Liu, F., Duan, N., Xu, Q., Hong, Y. (eds) Natural Language Processing and Chinese Computing. NLPCC 2023. Lecture Notes in Computer Science(), vol 14302. Springer, Cham. https://doi.org/10.1007/978-3-031-44693-1_22
Download citation
DOI: https://doi.org/10.1007/978-3-031-44693-1_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44692-4
Online ISBN: 978-3-031-44693-1
eBook Packages: Computer ScienceComputer Science (R0)