Contamination-Reduced Multi-View Reconstruction for Graph Anomaly Detection
Open Access
- 1 February 2026
- journal article
- research article
- Published by MDPI AG in Technologies
- Vol. 14 (2) , 85
Abstract
Graph anomaly detection (GAD) is pivotal for security-critical applications like cybersecurity and financial fraud detection. While reconstruction-based Graph Neural Networks (GNNs) are prevalent, their efficacy is often compromised by two phenomena: (1) anomaly overfitting, where expressive models capture anomalous patterns, and (2) homophily-induced attenuation, where message passing smooths localized anomaly cues. This paper proposes CLEAN-GAD, a contamination-aware framework that mitigates anomaly influence during training through multi-view robust learning. Specifically, we develop a contrastive augmentation module that utilizes local inconsistency scores to identify and suppress pseudo-anomalous nodes and edges, thereby yielding a purified augmented view. To capture diverse anomaly signals, a frequency-adaptive encoder with dual-pass channels is designed to integrate low- and high-frequency information. Furthermore, we introduce a distribution-separation regularizer and cross-view alignment to stabilize learning and resolve view shifts. Theoretical analysis confirms that reducing the contamination ratio expands the reconstruction-risk gap between normal and anomalous nodes, inherently boosting detection performance. Extensive experiments on multiple benchmark datasets from various domains demonstrate the superior anomaly detection performance of CLEAN-GAD.
Keywords
Funding Information
- National Natural Science Foundation of China (U2336202)
This publication has 33 references indexed in Scilit:
- G-CutMix: A CutMix-based graph data augmentation method for bot detection in social networksPLOS ONE, 2025
- Rethinking Unsupervised Graph Anomaly Detection With Deep Learning: Residuals and ObjectivesIEEE Transactions on Knowledge and Data Engineering, 2024
- Data Augmentation for Deep Graph LearningACM SIGKDD Explorations Newsletter, 2022
- Internet Financial Fraud Detection Based on Graph LearningIEEE Transactions on Computational Social Systems, 2022
- Contrastive Attributed Network Anomaly Detection with Data Augmentation2022
- Anomaly Detection on Attributed Networks via Contrastive Self-Supervised LearningIEEE Transactions on Neural Networks and Learning Systems, 2021
- One-class graph neural networks for anomaly detection in attributed networksNeural Computing and Applications, 2021
- Graph Neural Network for Fraud Detection via Spatial-Temporal AttentionIEEE Transactions on Knowledge and Data Engineering, 2020
- Variational Graph Auto-EncodersarXiv, 2016
- Collective Classification in Network DataAI Magazine, 2008