ADKGD: Anomaly Detection in Knowledge Graphs with Dual-Channel Training
ACM Transactions on Asian and Low-Resource Language Information Processing · 30.11.2025 · 24 (11) · 1-29
DOI: 10.1145/3748321 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Asian and Low-Resource Language Information Processing, online erschienen am 24.10.2025. Verfasst von Jiayang Wu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 52 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Guangzhou Basic and Applied Basic Research Foundation, Engineering Research Center of Trustworthy AI, Ministry of Education.
Abstract (Originalsprache)
In the current development of large language models (LLMs), it is important to ensure the accuracy and reliability of the underlying data sources. LLMs are critical for various applications, but they often suffer from hallucinations and inaccuracies due to knowledge gaps in the training data. Knowledge graphs (KGs), as a powerful structural tool, could serve as a vital external information source to mitigate the aforementioned issues. By providing a structured and comprehensive understanding of real-world data, KGs enhance the performance and reliability of LLMs. However, it is common that errors exist in KGs while extracting triplets from unstructured data to construct KGs. This could lead to degraded performance in downstream tasks such as question-answering and recommender systems. Therefore, anomaly detection in KGs is essential to identify and correct these errors. This article presents an anomaly detection algorithm in knowledge graphs with dual-channel learning (ADKGD). ADKGD leverages a dual-channel learning approach to enhance representation learning from both the entity-view and triplet-view perspectives. Furthermore, using a cross-layer approach, our framework integrates internal information aggregation and context information aggregation. We introduce a kullback-leibler (KL)-loss component to improve the accuracy of the scoring function between the dual channels. To evaluate ADKGD’s performance, we conduct empirical studies on three real-world KGs: WN18RR, FB15K, and NELL-995. Experimental results demonstrate that ADKGD outperforms state-of-the-art anomaly detection algorithms. The source code and datasets are publicly available at https://github.com/csjywu1/ADKGD .
Förderung
- National Natural Science Foundation of China
- Guangzhou Basic and Applied Basic Research Foundation
- Engineering Research Center of Trustworthy AI, Ministry of Education
- Guangdong Key Laboratory of Data Security and Privacy Preserving
Zitieren
APA
Wu, J., Gan, W., Zhang, J., & Yu, P. (2025). ADKGD: Anomaly Detection in Knowledge Graphs with Dual-Channel Training. ACM Transactions on Asian and Low-Resource Language Information Processing, 24(11), 1-29. https://doi.org/10.1145/3748321
Vancouver
Wu J, Gan W, Zhang J, Yu P. ADKGD: Anomaly Detection in Knowledge Graphs with Dual-Channel Training. ACM Transactions on Asian and Low-Resource Language Information Processing. 2025;24(11):1-29. doi:10.1145/3748321
BibTeX
@article{Wu2025,
author = {Wu, Jiayang and Gan, Wensheng and Zhang, Jiahao and Yu, Philip},
title = {ADKGD: Anomaly Detection in Knowledge Graphs with Dual-Channel Training},
journal = {ACM Transactions on Asian and Low-Resource Language Information Processing},
year = {2025},
volume = {24},
number = {11},
pages = {1--29},
doi = {10.1145/3748321}
}
EUVIMED