Entity alignment aims to match identical entities across different knowledge graphs (KGs). Graph neural network-based entity alignment methods have achieved promising results in Euclidean space. However, KGs often contain complex structures, including both local and hierarchical ones, which make it challenging to efficiently represent them within a single space. In this paper, we proposed a novel method UniEA, which unifies dual-space embedding to preserve the intrinsic structure of KGs. Specifically, we learn graph structure embedding in both Euclidean and hyperbolic spaces simultaneously to maximize the consistency between the embedding in both spaces. Moreover, we employ contrastive learning to mitigate the misalignment issues caused by similar entities, where embedding of similar neighboring entities within the KG become too close in distance. Extensive experiments on benchmark datasets demonstrate that our method achieves state-of-the-art performance in structure-based EA. Our code is available at https://github.com/wonderCS1213/UniEA.

翻译：实体对齐旨在匹配不同知识图谱中的相同实体。基于图神经网络的实体对齐方法在欧几里得空间中已取得显著成果。然而，知识图谱通常包含复杂的结构，包括局部结构与层次结构，这使得在单一空间中高效表征图谱具有挑战性。本文提出了一种新颖的方法UniEA，该方法通过统一双空间嵌入来保持知识图谱的内在结构。具体而言，我们同时在欧几里得空间与双曲空间中学习图结构嵌入，以最大化两个空间嵌入间的一致性。此外，我们采用对比学习来缓解由相似实体引起的错位问题，即知识图谱中相似邻接实体的嵌入在距离上过于接近。在基准数据集上的大量实验表明，我们的方法在基于结构的实体对齐任务中实现了最先进的性能。代码公开于https://github.com/wonderCS1213/UniEA。