Attr-Int: A Simple and Effective Entity Alignment Framework for Heterogeneous Knowledge Graphs

Abstract

Entity alignment (EA) refers to the task of linking entities in different knowledge graphs (KGs). Existing EA methods rely heavily on structural isomorphism. However, in real-world KGs, aligned entities usually have non-isomorphic neighborhood structures, which paralyses the application of these structure-dependent methods. In this paper, we investigate and tackle the problem of entity alignment between heterogeneous KGs. First, we propose two new benchmarks to closely simulate real-world EA scenarios of heterogeneity. Then we conduct extensive experiments to evaluate the performance of representative EA methods on the new benchmarks. Finally, we propose a simple and effective entity alignment framework called Attr-Int, in which innovative attribute information interaction methods can be seamlessly integrated with any embedding encoder for entity alignment, improving the performance of existing entity alignment techniques. Experiments demonstrate that our framework outperforms the state-of-the-art approaches on two new benchmarks.

Figures (2)

• Figure 1: Overall architecture of proposed framework.
• Figure 2: Percentage of coverage rate of entity pairs in each stage of the original benchmark datasets and new benchmark datasets. The x-axis represents the coverage rate of entity pairs, while the y-axis represents the proportion of all benchmark datasets.