Abstract
As an important research work in knowledge fusion, entity alignment can promote the sharing and integration of multi-source knowledge graphs. Recently, entity alignment based on graph neural networks has received a lot of attention for its ability to capture the topology of entities, but it ignores the noise in neighbor subgraphs and the impact of distant neighbors on central entities. In addition, the knowledge graph is a sparse structure, with the vast majority of entities obeying the long-tail effect.But existing works pay little attention to the alignment of long-tail entities. To address the above problems, this paper proposes an entity alignment approach, which aggregates bi-directional multi-hop neighbors to enrich the context of the central entity, and uses entity names to supply entities with less structural information. The feature fusion module can dynamically adjust weights for the significance of different features. Experimental results show that the overall performance of our model is superior than that of GNN-based methods.
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
References
Bordes, A., Usunier, N., Garcia-Duran, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multirelational data. In: NeurIPS, pp. 2787–2795 (2013)
Wang, Z., Lv, Q., Lan, X., Zhang, Y.: Cross-lingual knowledge graph alignment via graph convolutional networks. In: EMNLP, pp. 349–357 (2018)
Sun, Z., Wang, C., Hu, W., Chen, M., Dai, J., Zhang, W., Qu, Y.: Knowledge graph alignment network with gated multi-hop neighborhood aggregation. In: AAAI 34(01) pp. 222–229 (2020)
Xu, K., et al.: Cross-lingual knowledge graph alignment via graph matching neural network. In: ACL, pp. 3156–3161 (2019)
Wu, Y., Liu, X., Feng, Y., Wang, Z., Yan, R., Zhao, D.: Relation-aware entity alignment for heterogeneous knowledge graphs. In: IJCAI, pp. 5278–5284 (2019)
Wu, Y., Liu, X., Feng, Y., Wang, Z., Zhao, D.: Jointly Learning Entity and Relation Representations for Entity Alignment. In: EMNLP-IJCNLP, pp. 240–249 (2019)
Cao, Y., Liu, Z., Li, C., Li, J., Chua, T.-S.: Multi-channel graph neural network for entity alignment. In: ACL, pp. 1452–1461 (2019)
Wu, Y., Liu, X., Feng, Y., Wang, Z., Zhao, D.: Neighborhood matching network for entity alignment. In: ACL, pp. 6477–6487 (2020)
Zhang, Q., Sun, Z., Hu, W., Chen, M., Guo, L., Qu, Y.: Multi-view knowledge graph embedding for entity alignment. In: IJCAI, pp. 5429–5435 (2019)
Pei, S., Yu, L., Hoehndorf, R., Zhang, X.: Semi-supervised entity alignment via knowledge graph embedding with awareness of degree difference. In: WWW, pp. 3130–3136 (2019)
Chen, M., Tian, Y., Yang, M., Zaniolo, C.: Multilingual knowledge graph embeddings for cross-lingual knowledge alignment. In: IJCAI, pp. 1511–1517 (2017)
Seo, M., Kembhavi, A., Farhadi, A., Hajishirzi, H.: Bidirectional attention flow for machine comprehension. arXiv preprint 1611.01603 (2016)
Liu, F., Chen, M., Roth, D., Collier, N.: Visual Pivoting for (Unsupervised) Entity Alignment. In: AAAI 35(5), pp. 4257–4266 (2021)
Zeng, W., Zhao, X., Wang, W., Tang, J., Tan, Z.: Degree-aware alignment for entities in tail. In: SIGIR, pp. 811–820 (2020)
Xin, K., Sun, Z., Hua, W., Hu, W., Zhou, X.: Informed multi-context entity alignment. In: WSDM. pp. 1197–1205 (2022)
Sun, Z., Hu, W., Li, C.: Cross-Lingual Entity Alignment via Joint Attribute-Preserving Embedding. In: d’Amato, C., et al. (eds.) ISWC 2017. LNCS, vol. 10587, pp. 628–644. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-68288-4_37
Jiang, S., Nie, T., Shen, D., Kou, Y., Yu, G.: Entity Alignment of Knowledge Graph by Joint Graph Attention and Translation Representation. In: Xing, C., Fu, X., Zhang, Y., Zhang, G., Borjigin, C. (eds.) WISA 2021. LNCS, vol. 12999, pp. 347–358. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87571-8_30
Chen, M., Tian, Y., Chang, K.-W., Skiena, S., Zaniolo, C.: Co-training embeddings of knowledge graphs and entity descriptions for cross-lingual entity alignment. In: IJCAI, pp. 3998–4004 (2018)
Liu, Z., Cao, Y., Pan, L., Li, J., Chua, T.: Exploring and Evaluating Attributes, Values, and Structures for Entity Alignment. In: EMNLP, pp. 6355–6364 (2020)
Sun, Z., et al.: A benchmarking study of embedding-based entity alignment for knowledge graphs. In: Proceedings of the VLDB Endowment 13(11), pp. 2326–2340 (2020)
Azzalini, F., Jin, S., Renzi, M., Tanca, L.: Blocking techniques for entity linkage: a semantics-based approach. Data Science and Engineering 6(1), 20–38 (2020). https://doi.org/10.1007/s41019-020-00146-w
Sun, Z., Hu, W., Zhang, Q., Qu, Y.: Bootstrapping entity alignment with knowledge graph embedding. In: IJCAI, pp. 4396–4402 (2018)
Acknowledgment
This work was supported by the National Natural Science Foundation of China (62072086, 62172082, 62072084), the Fundamental Research Funds for the central Universities (N2116008).
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
Bai, J., Nie, T., Shen, D., Kou, Y., Yu, G. (2022). Bi-Directional Neighborhood-Aware Network for Entity Alignment in Knowledge Graphs. In: Zhao, X., Yang, S., Wang, X., Li, J. (eds) Web Information Systems and Applications. WISA 2022. Lecture Notes in Computer Science, vol 13579. Springer, Cham. https://doi.org/10.1007/978-3-031-20309-1_6
Download citation
DOI: https://doi.org/10.1007/978-3-031-20309-1_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20308-4
Online ISBN: 978-3-031-20309-1
eBook Packages: Computer ScienceComputer Science (R0)