Knowing the No-match: Entity Alignment with Dangling Cases
This paper studies a new problem setting of entity alignment for knowledge graphs (KGs). Since KGs possess different sets of entities, there could be entities that cannot find alignment across them, leading to the problem of dangling entities. As the first attempt to this problem, we construct a new dataset and design a multi-task learning framework for both entity alignment and dangling entity detection. The framework can opt to abstain from predicting alignment for the detected dangling entities. We propose three techniques for dangling entity detection that are based on the distribution of nearest-neighbor distances, i.e., nearest neighbor classification, marginal ranking and background ranking. After detecting and removing dangling entities, an incorporated entity alignment model in our framework can provide more robust alignment for remaining entities. Comprehensive experiments and analyses demonstrate the effectiveness of our framework. We further discover that the dangling entity detection module can, in turn, improve alignment learning and the final performance. The contributed resource is publicly available to foster further research.
Code (1)
Tasks
Abstention PredictionEntity AlignmentKnowledge GraphsSimilar Papers 제목 키워드 기반
Lambda: Learning Matchable Prior For Entity Alignment with Unlabeled Dangling Cases
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 …
Contrastive LearningEntity AlignmentRepresentation LearningDangling-Aware Entity Alignment with Mixed High-Order Proximities
We study dangling-aware entity alignment in knowledge graphs (KGs), which is an underexplored but important problem. As different KGs are naturally constructed by different sets of entities, a KG commonly contains some d…
Entity AlignmentKnowledge GraphsVocal Bursts Intensity PredictionDangling-Aware Entity Alignment with Mixed High-Order Proximities
We study dangling-aware entity alignment in knowledge graphs (KGs), which is an underexplored but important problem. As different KGs are naturally constructed by different sets of entities, a KG commonly contains some d…
Entity AlignmentKnowledge GraphsVocal Bursts Intensity PredictionSemi-constraint Optimal Transport for Entity Alignment with Dangling Cases
Entity alignment (EA) merges knowledge graphs (KGs) by identifying the equivalent entities in different graphs, which can effectively enrich knowledge representations of KGs. However, in practice, different KGs often inc…
Entity AlignmentKnowledge GraphsMetric LearningWord EmbeddingsAn Accurate Unsupervised Method for Joint Entity Alignment and Dangling Entity Detection
Knowledge graph integration typically suffers from the widely existing dangling entities that cannot find alignment cross knowledge graphs (KGs). The dangling entity set is unavailable in most real-world scenarios, and m…
Entity AlignmentKnowledge Graphs