Attr-Int: A Simple and Effective Entity Alignment Framework for Heterogeneous Knowledge Graphs
This addresses the problem of entity alignment in real-world heterogeneous knowledge graphs, where existing methods fail due to non-isomorphic structures, representing an incremental improvement.
The paper tackles entity alignment between heterogeneous knowledge graphs by proposing a new framework, Attr-Int, which integrates attribute information with embedding encoders, and it outperforms state-of-the-art methods on two new benchmarks.
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.