Abstract
As an essential method of knowledge graph fusion, entity alignment aims to find entities that refer to the same real-world object in different knowledge graphs. Current entity alignment methods usually adopt extra information such as entity names, attribute triples except for structural information of the knowledge graph. However, due to the difficult availability and possibly low effectiveness of extra information, it is necessary to improve the performance of entity alignment when using only structural information. In this paper, a novel entity alignment method based on the multiscale convolutional graph network (MCEA) is proposed, which utilizes only structural information of the graph for entity alignment. Firstly, the convolution region of long-tail entities is extended to enhance the ability of information capture of the graph network. Secondly, intermediate results from semi-supervised learning are introduced to negative sampling in order to improve sampling quality. Thirdly, the stable marriage algorithm is chosen as the alignment strategy to obtain final alignment results. The experimental results show that this method has achieved better performance on Hits@K and MRR than the state-of-the-art methods, especially in the case of less labeled data. Moreover, we also find that the impact of the alignment strategy has become limited when the model generates sufficient accurate entity embeddings.
Similar content being viewed by others
References
Lin L, et al. (2020) A similarity model based on reinforcement local maximum connected same destination structure oriented to disordered fusion of knowledge graphs. Appl Intell 50:2867–2886
Chen L, Tian X, Tang X, et al. (2021) Multi-information embedding based entity alignment. Appl Intell 51:8896–8912
Devlin J, et al. (2019) BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT. Association for computational linguistics, Minneapolis, pp 4171–4186
Mao X et al (2020) MRAEA: An efficient and robust entity alignment approach for cross-lingual knowledge graph. In: Proceedings of the 13th international conference on web search and data mining. Association for Computing Machinery, New York, pp 420–428
Sun Z, et al. (2018) Bootstrapping entity alignment with knowledge graph embedding. In: IJCAI, pp 4396–4402
Sun Zequn, et al. (2019) Transedge: translating relation-contextualized embeddings for knowledge graphs. In: SEMWEB
Mao X et al (2020) Relational Reflection Entity Alignment. In: Proceedings of the 29th ACM international conference on information & knowledge management. Association for Computing Machinery, New York, pp 1095–1104
Bordes A, et al. (2013) Translating Embeddings for Modeling Multi-relational Data. In: NIPS. Curran Associates Inc., Red Hook, NY, pp 2787–2795
McVitie D, Wilson LB (1971) The stable marriage problem. Commun. ACM 14:486–490
Fey M, Lenssen JE, Morris C, Masci J, Kriege NM (2020) Deep graph matching consensus. In: International conference on learning representations. ICLR 2020
Zhu R, et al. (2021) RAGA: relation-aware graph attention networks for global entity alignment. In: PAKDD. Springer, Cham, pp 501–513
Zeng W, et al. (2021) Towards Entity alignment in the open world: an unsupervised approach. In: DASFAA. Springer, Cham, pp 272–289
Pennington J, et al. (2014) Glove: Global Vectors for word representation. In: EMNLP. Association for Computational Linguistics, Doha, pp 1532–1543
Sun Z, Hu W, Li C (2017) Cross-lingual entity alignment via joint attribute-preserving embedding. In: International Semantic Web Conference. Springer, Cham, pp 628–644
Wang Z, et al. (2018) Cross-lingual knowledge graph alignment via graph convolutional networks. In: Proceedings of the 2018 conference on empirical methods in natural language processing. Association for Computational Linguistics, Belgium, pp 349–357
He F, et al. (2019) Unsupervised entity alignment using attribute triples and relation triples. In: DASFAA. Springer, Cham, pp 367–382
Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: Proceedings of ICLR. OpenReview.net, France
Zeng W, et al. (2020) Collective entity alignment via adaptive features. In: 2020 IEEE 36th International Conference on Data Engineering (ICDE), pp 1870–1873
Joulin A, et al. (2017) Bag of tricks for efficient text classification, Association for Computational Linguistics, Spain
Liu F, Chen M, Roth D, et al. (2021) Visual pivoting for (unsupervised) entity alignment. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)
Chen M, et al. (2017) Multilingual knowledge graph embeddings for cross-lingual knowledge alignment. In: IJCAI. AAAI Press, pp 1511–1517
Cao Y, et al. (2019) Multi-channel graph neural network for entity alignment. In: Proceedings of the 57th annual meeting of the association for computational linguistics. Association for Computational Linguistics, Florence, Italy, pp 1452–1461
Conneau A, Lample G, Ranzato M, Denoyer L, Jégou H (2018a) Word translation without parallel data. In proceedings of ICLR, 2018
He K, et al. (2015) Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: 2015 IEEE International conference on computer vision (ICCV), pp 1026–1034
Petar V, Cucurull G, Casanova A, Romero A, Lio P, Bengio Y (2018) Graph attention networks. In: International conference on learning representations (ICLR)
Sun Z, Wang C, Hu W, et al. (2020) Knowledge graph alignment network with gated multi-hop neighborhood aggregation. Proc AAAI Conf Artif Intell 34(01):222–229
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Qi, D., Chen, S., Sun, X. et al. A multiscale convolutional gragh network using only structural information for entity alignment. Appl Intell 53, 7455–7465 (2023). https://doi.org/10.1007/s10489-022-03916-3
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-03916-3