Adaptive Graph Convolutional Network for Knowledge Graph Entity Alignment

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. 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. In this paper, we propose a lightweight framework with no training parameters for both supervised and unsupervised EA. Based on the Sinkhorn algorithm, we design a reliability measure for pseudo 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. Extensive experiments on benchmark datasets demonstrate that our framework outperforms the state-of-the-art methods in both supervised and unsupervised settings.