Knowledge Graph Error Detection with Contrastive Confidence Adaption
This addresses error detection in knowledge graphs for AI applications, but it is incremental as it builds on existing methods by adding textual information and contrastive learning.
The paper tackled the problem of detecting errors in knowledge graphs, which often struggle with semantically-similar correct triplets, by proposing CCA, a model that integrates textual and graph structural information using interactive contrastive learning, and it outperformed state-of-the-art baselines, especially in detecting semantically-similar and adversarial noise.
Knowledge graphs (KGs) often contain various errors. Previous works on detecting errors in KGs mainly rely on triplet embedding from graph structure. We conduct an empirical study and find that these works struggle to discriminate noise from semantically-similar correct triplets. In this paper, we propose a KG error detection model CCA to integrate both textual and graph structural information from triplet reconstruction for better distinguishing semantics. We design interactive contrastive learning to capture the differences between textual and structural patterns. Furthermore, we construct realistic datasets with semantically-similar noise and adversarial noise. Experimental results demonstrate that CCA outperforms state-of-the-art baselines, especially in detecting semantically-similar noise and adversarial noise.