Type Information-Assisted Self-Supervised Knowledge Graph Denoising
Sun, Jiaqi Zheng, Yujia Dong, Xinshuai Dai, Haoyue Zhang, Kun
Sun, Jiaqi
Zheng, Yujia
Dong, Xinshuai
Dai, Haoyue
Zhang, Kun
Supervisor
Department
Machine Learning
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Knowledge graphs serve as critical resources supporting intelligent systems, but they can be noisy due to imperfect automatic generation processes. Existing approaches to noise detection often rely on external facts, logical rule constraints, or structural embeddings. These methods are often challenged by imperfect entity alignment, flexible knowledge graph construction, and overfitting on structures. In this paper, we propose to exploit the consistency between entity and relation type information for noise detection, resulting a novel self-supervised knowledge graph denoising method that avoids those problems. We formalize type inconsistency noise as triples that deviate from the majority with respect to type-dependent reasoning along the topological structure. Specifically, we first extract a compact representation of a given knowledge graph via an encoder that models the type dependencies of triples. Then, the decoder reconstructs the original input knowledge graph based on the compact representation. It is worth noting that, our proposal has the potential to address the problems of knowledge graph compression and completion, although this is not our focus. For the specific task of noise detection, the discrepancy between the reconstruction results and the input knowledge graph provides an opportunity for denoising, which is facilitated by the type consistency embedded in our method. Experimental validation demonstrates the effectiveness of our approach in detecting potential noise in real-world data.
Citation
J. Sun, Y. Zheng, X. Dong, H. Dai, and K. Zhang, “Type Information-Assisted Self-Supervised Knowledge Graph Denoising,” in Proc. 28th Int. Conf. Artif. Intell. Stat. (AISTATS 2025), vol. 258, Proc. Mach. Learn. Res., Mai Khao, Thailand, May 3–5, 2025, pp. 964–972.
Source
Proceedings of Machine Learning Research
Conference
28th International Conference on Artificial Intelligence and Statistics, AISTATS 2025
Keywords
Background Noise, Graph Embeddings, Graph Structures, Graphic Methods, Knowledge Graph, Spurious Signal Noise, Undirected Graphs, Automatic Generation, Compact Representation, Critical Resources, De-noising, Embeddings, Generation Process, Knowledge Graphs, Logical Rules, Noise Detection, Type Information, Intelligent Systems
Subjects
Source
28th International Conference on Artificial Intelligence and Statistics, AISTATS 2025
Publisher
ML Research Press