Iterative Entity Alignment with Improved Neural Attribute Embedding

Entity alignment (EA) aims to detect equivalent entities in different knowledge graphs (KGs), which can facilitate the integration of knowledge from multiple sources. Current EA methods usually harness KG embeddings to project entities in various KGs into the same low-dimensional space, where equivalent entities are placed close to each other. Nevertheless, most methods fail to take fully advantage of other sources of information, e.g., attribute information, and overlook the negative impact brought by lack of labelled data. To overcome these deficiencies, in this paper, we propose to generate neural attribute representation by considering both local and global signals. Besides, entity representations are refined via an iterative training process on the neural network. We evaluate our proposal on real-life datasets against state-of-the-art methods, and the results demonstrate the effectiveness of our solution.