Knowledge Graph Error Detection with Contrastive Confidence Adaption

11citations
arXiv:2312.12108
11
citations
#780
in AAAI 2024
of 2289 papers
3
Top Authors
4
Data Points

Abstract

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.

Citation History

Jan 28, 2026
0
Feb 13, 2026
11+11
Feb 13, 2026
11
Feb 13, 2026
11