DCOR: Anomaly Detection in Attributed Networks via Dual Contrastive Learning Reconstruction

TL;DR

DCOR is a novel anomaly detection method for attributed networks that combines reconstruction and contrastive learning within a GNN framework, effectively identifying subtle and emerging anomalies.

Contribution

Introduces DCOR, integrating reconstruction-based anomaly detection with contrastive learning on attributed networks, addressing attribute impact and emerging anomalies.

Findings

DCOR outperforms state-of-the-art methods on benchmark datasets.

Effective in detecting subtle and emerging anomalies.

Demonstrates the potential to uncover new anomaly patterns.

Abstract

Anomaly detection using a network-based approach is one of the most efficient ways to identify abnormal events such as fraud, security breaches, and system faults in a variety of applied domains. While most of the earlier works address the complex nature of graph-structured data and predefined anomalies, the impact of data attributes and emerging anomalies are often neglected. This paper introduces DCOR, a novel approach on attributed networks that integrates reconstruction-based anomaly detection with Contrastive Learning. Utilizing a Graph Neural Network (GNN) framework, DCOR contrasts the reconstructed adjacency and feature matrices from both the original and augmented graphs to detect subtle anomalies. We employed comprehensive experimental studies on benchmark datasets through standard evaluation measures. The results show that DCOR significantly outperforms state-of-the-art methods. Obtained results demonstrate the efficacy of proposed approach in attributed networks with the potential of uncovering new patterns of anomalies.