We investigate the entity alignment (EA) problem with unlabeled dangling cases, meaning that partial entities have no counterparts in the other knowledge graph (KG), and this type of entity remains unlabeled. To address this challenge, we propose the framework \textit{Lambda} for dangling detection and then entity alignment. Lambda features a GNN-based encoder called KEESA with spectral contrastive learning for EA and a positive-unlabeled learning algorithm for dangling detection called iPULE. iPULE offers theoretical guarantees of unbiasedness, uniform deviation bounds, and convergence. Experimental results demonstrate that each component contributes to overall performances that are superior to baselines, even when baselines additionally exploit 30\% of dangling entities labeled for training.

翻译：本文研究了包含无标签悬空实体的知识图谱实体对齐问题，即部分实体在另一个知识图谱中没有对应实体，且此类实体未被标注。为应对这一挑战，我们提出了用于悬空实体检测及后续实体对齐的框架 \textit{Lambda}。Lambda 的核心包括：一个基于图神经网络的编码器 KEESA，它采用谱对比学习进行实体对齐；以及一个用于悬空实体检测的正例-无标签学习算法 iPULE。iPULE 在理论上保证了无偏性、一致偏差界和收敛性。实验结果表明，即使基线模型额外利用了 30% 已标注的悬空实体进行训练，Lambda 的各个组件仍能协同提升整体性能，并显著优于现有基线方法。