Global-Local Complementary Fusion: Unsupervised Graph Anomaly Detection via Diffusion Reconstruction and Contrastive Learning
Symmetry · 03.06.2026 · 18 (6) · 968
DOI: 10.3390/sym18060968 ↗Kurz gefasst
Fachartikel in der Zeitschrift Symmetry, online erschienen am 03.06.2026. Verfasst von Ruibin Hu und 6 weiteren Autor:innen. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, National Social Science Fund of China, Key Project of Natural Science Foundation of Zhejiang Province.
Abstract (Originalsprache)
Anomaly detection on attributed graphs is essential for scientific integrity, cybersecurity, and financial oversight, where abnormal patterns often manifest as breaks in structure or attributes. However, existing unsupervised methods are difficult to combine both global and local perspectives to detect anomalies. To address this issue, we propose DCGAD, a unified unsupervised framework that captures anomalies by fusing global reconstruction error and local view inconsistency. Our model leverages diffusion reconstruction to strengthen global semantic information, employing two parallel autoencoders to reconstruct the graph structure based on the original features and diffusion-enhanced features, respectively, to capture global structural differences. Complementarily, the model samples two local subgraph views per target node and uses multi-view contrastive learning to evaluate local contextual inconsistencies. By jointly optimizing these two complementary objectives, our proposed model achieves collaborative use of local and global information. Extensive experiments on six real-world graph datasets show that DCGAD outperforms other state-of-the-art approaches, achieving excellent scores on citation networks and significant gains on social and collaborative platforms.
Förderung
- National Natural Science Foundation of China
- National Social Science Fund of China
- Key Project of Natural Science Foundation of Zhejiang Province
- Zhejiang Province Leading Geese Plan
- Zhejiang Province Province-Land Synergy Program
Zitieren
APA
Hu, R., Chen, Q., Xu, H., Wang, R., Jin, H., Huang, X., & Zhu, X. (2026). Global-Local Complementary Fusion: Unsupervised Graph Anomaly Detection via Diffusion Reconstruction and Contrastive Learning. Symmetry, 18(6), 968. https://doi.org/10.3390/sym18060968
Vancouver
Hu R, Chen Q, Xu H, Wang R, Jin H, Huang X, et al. Global-Local Complementary Fusion: Unsupervised Graph Anomaly Detection via Diffusion Reconstruction and Contrastive Learning. Symmetry. 2026;18(6):968. doi:10.3390/sym18060968
BibTeX
@article{Hu2026,
author = {Hu, Ruibin and Chen, Qian and Xu, Huiying and Wang, Ruidong and Jin, Huazhen and Huang, Xiao and Zhu, Xinzhong},
title = {Global-Local Complementary Fusion: Unsupervised Graph Anomaly Detection via Diffusion Reconstruction and Contrastive Learning},
journal = {Symmetry},
year = {2026},
volume = {18},
number = {6},
pages = {968},
doi = {10.3390/sym18060968}
}
EUVIMED