Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs
This work addresses entity alignment for knowledge graphs, which is crucial for integrating multi-relational data, but it appears incremental as it builds on existing embedding-based methods by enhancing relation modeling.
The paper tackles the problem of entity alignment in heterogeneous knowledge graphs by proposing a Relation-aware Dual-Graph Convolutional Network (RDGCN) to better capture complex relation information, resulting in improved and more robust performance over state-of-the-art methods on three real-world cross-lingual datasets.
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.