Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs

TL;DR

This paper introduces a relation-aware dual-graph convolutional network that improves entity alignment in heterogeneous knowledge graphs by better capturing complex relation information and neighboring structures.

Contribution

It proposes a novel RDGCN model that incorporates relation information through attentive interactions and dual-graph structures for enhanced entity alignment.

Findings

Outperforms state-of-the-art methods on three real-world datasets.

Effectively captures complex relation information in multi-relational KGs.

Provides more robust and accurate entity alignment results.

Abstract

Entity alignment is the task of linking entities with the same real-world identity from different knowledge graphs (KGs), which has been recently dominated by embedding-based methods. Such approaches work by learning KG representations so that entity alignment can be performed by measuring the similarities between entity embeddings. While promising, prior works in the field often fail to properly capture complex relation information that commonly exists in multi-relational KGs, leaving much room for improvement. In this paper, we propose a novel Relation-aware Dual-Graph Convolutional Network (RDGCN) to incorporate relation information via attentive interactions between the knowledge graph and its dual relation counterpart, and further capture neighboring structures to learn better entity representations. Experiments on three real-world cross-lingual datasets show that our approach delivers better and more robust results over the state-of-the-art alignment methods by learning better KG representations.