Adaptive Graph Convolutional Network for Knowledge Graph Entity Alignment

Renbo Zhu, Xukun Luo, Meng Ma, Ping Wang


Abstract
Entity alignment (EA) aims to identify equivalent entities from different Knowledge Graphs (KGs), which is a fundamental task for integrating KGs. Throughout its development, Graph Convolutional Network (GCN) has become one of the mainstream methods for EA. These GCN-based methods learn the representations of entities from two KGs by message passing mechanism and then make alignments via measuring the similarity between entity embeddings. The key idea that GCN works in EA is that entities with similar neighbor structures are highly likely to be aligned. However, the noisy neighbors of entities transfer invalid information, drown out equivalent information, lead to inaccurate entity embeddings, and finally reduce the performance of EA. Based on the Sinkhorn algorithm, we design a reliability measure for potential equivalent entities and propose Adaptive Graph Convolutional Network to deal with neighbor noises in GCN. During the training, the network dynamically updates the adaptive weights of relation triples to weaken the propagation of noises. While calculating entity similarity, it comprehensively considers the self-similarity and neighborhood similarity of the entity pair to alleviate the influence of noises. Furthermore, we design a straightforward but efficient strategy to construct pseudo alignments for unsupervised EA. Extensive experiments on benchmark datasets demonstrate that our framework outperforms the state-of-the-art methods in both supervised and unsupervised settings.
Anthology ID:
2022.findings-emnlp.444
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6011–6021
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.444
DOI:
10.18653/v1/2022.findings-emnlp.444
Bibkey:
Cite (ACL):
Renbo Zhu, Xukun Luo, Meng Ma, and Ping Wang. 2022. Adaptive Graph Convolutional Network for Knowledge Graph Entity Alignment. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 6011–6021, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Adaptive Graph Convolutional Network for Knowledge Graph Entity Alignment (Zhu et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.444.pdf