EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DGAM: Dual-Guided Anomaly Mining for Semi-Supervised Graph Anomaly Detection

Xingxuan Li, Ting Guo, Zhen Tian

Information · 23.05.2026 · 17 (6) · 521

DOI: 10.3390/info17060521 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Information, online erschienen am 23.05.2026. Verfasst von Xingxuan Li und 2 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Natural Science Foundation of Shanxi Province, Shanxi Provincial Key Laboratory, Shanxi Higher Education Institutions Science and Technology Innovation Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

For the challenging scenario in which only normal node labels are available in semi-supervised graph anomaly detection, existing generative methods usually synthesize abnormal nodes through random perturbation or feature interpolation. However, these methods fail to consider node abnormality comprehensively from both structural and attribute perspectives, resulting in generated pseudo-anomalies of limited quality and insufficient reliability. In order to address this problem, we propose DGAM (dual-guided anomaly mining), a framework for selecting pseudo-anomaly nodes based on the dual-index measurement of topological anomaly and feature consistency. The core of the framework is the joint anomaly evaluation module, which quantifies node anomaly through two computable metrics. The topological boundary score (TBS) measures the boundary of a node’s topological position based on the proportion of connections between a node and labeled normal nodes in its K-hop neighborhood. The feature deviation score (FDS) evaluates the consistency of a node’s local features by calculating the average cosine similarity between its features and those of its K-hop neighbors. The module selects a fixed set of nodes with higher comprehensive anomaly scores from the labeled normal nodes as pseudo-anomalies, so as to construct a training set containing explicit supervision signals. The model adopts a shared encoder architecture and jointly optimizes the classification loss based on pseudo-labels and the embedding regularization loss of the graph nodes to learn a more discriminative node representation. Experimental results on multiple real-world graph datasets show that DGAM can stably improve anomaly detection performance, effectively verifying the effectiveness of the proposed screening mechanism and joint training strategy.

Förderung

  • The Natural Science Foundation of Shanxi Province
  • Shanxi Provincial Key Laboratory
  • Shanxi Higher Education Institutions Science and Technology Innovation Project

Zitieren

APA

Li, X., Guo, T., & Tian, Z. (2026). DGAM: Dual-Guided Anomaly Mining for Semi-Supervised Graph Anomaly Detection. Information, 17(6), 521. https://doi.org/10.3390/info17060521

Vancouver

Li X, Guo T, Tian Z. DGAM: Dual-Guided Anomaly Mining for Semi-Supervised Graph Anomaly Detection. Information. 2026;17(6):521. doi:10.3390/info17060521

BibTeX
@article{Li2026,
  author = {Li, Xingxuan and Guo, Ting and Tian, Zhen},
  title = {DGAM: Dual-Guided Anomaly Mining for Semi-Supervised Graph Anomaly Detection},
  journal = {Information},
  year = {2026},
  volume = {17},
  number = {6},
  pages = {521},
  doi = {10.3390/info17060521}
}
Kostenlos starten →