Degree-Aware Alignment for Entities in Tail
Weixin Zeng, Xiang Zhao, Wei Wang, Jiuyang Tang, Zhen Tan
Abstract
Entity alignment (EA) is to discover equivalent entities in knowledge graphs (KGs), which bridges heterogeneous sources of information and facilitates the integration of knowledge. Existing EA solutions mainly rely on structural information to align entities, typically through KG embedding. Nonetheless, in real-life KGs, only a few entities are densely connected to others, and the rest majority possess rather sparse neighborhood structure. We refer to the latter as long-tail entities, and observe that such phenomenon arguably limits the use of structural information for EA.
Topics & Concepts
Computer sciencePhenomenonEmbeddingDegree (music)Rest (music)Information retrievalTheoretical computer scienceArtificial intelligenceEpistemologyMedicineAcousticsPhysicsPhilosophyCardiologyAdvanced Graph Neural NetworksData Quality and ManagementTopic Modeling