LargeEA: Aligning Entities for Large-scale Knowledge Graphs

Download PDF

Abstract

Entity alignment (EA) aims to find equivalent entities in different knowledge graphs (KGs). Recent years have witnessed a rapid development of EA. Current EA approaches align equivalent entities mainly rely on their structural features. The existing EA approaches have demonstrated considerable performance on the existing benchmarks. However, real-world KGs are typically much larger than the existing ones. Current EA approaches suffer from scalability issues, limiting their usage in real-world EA scenarios.To tackle this challenge, we propose LargeEA to align entities between large-scale KGs. LargeEA consists of two channels, i.e., structure channel and name channel. For the structure channel, we present METIS-CPS, a memory-saving mini-batch generation strategy, to partition large KGs into smaller mini-batches and to learn structural features of entities within each mini-batch independently. LargeEA is a general tool that can be easily integrated with any existing EA approach to learn entities’ structural features from large-scale KGs. For the name channel, we first introduce NFF, a name feature fusion method, to capture rich name features of entities without involving any complex training process. Then, we exploit a name-based data augmentation to generate seed alignment without any human intervention. Such design fits common real-world scenarios much better, as seed alignment is not always available. Finally, LargeEA derives the EA results by fusing the structural features and name features of entities. Since no widely-acknowledged EA benchmark is available for large-scale EA evaluation, we also develop a large-scale EA benchmark called DBP1M extracted from real-world KGs. Extensive experiments confirm the superiority of LargeEA against state-of-the-art competitors.