Hyperbolic Self-supervised Contrastive Learning Based Network Anomaly Detection

TL;DR

This paper introduces a hyperbolic self-supervised contrastive learning framework for network anomaly detection, effectively capturing hierarchical information in complex attributed networks, outperforming existing Euclidean-based methods.

Contribution

The paper proposes a novel hyperbolic contrastive learning approach that leverages hierarchical network information for improved anomaly detection in attributed graphs.

Findings

Outperforms baseline methods on four real-world datasets.

Effectively captures hierarchical information in complex networks.

Uses hyperbolic space for better anomaly scoring.

Abstract

Anomaly detection on the attributed network has recently received increasing attention in many research fields, such as cybernetic anomaly detection and financial fraud detection. With the wide application of deep learning on graph representations, existing approaches choose to apply euclidean graph encoders as their backbone, which may lose important hierarchical information, especially in complex networks. To tackle this problem, we propose an efficient anomaly detection framework using hyperbolic self-supervised contrastive learning. Specifically, we first conduct the data augmentation by performing subgraph sampling. Then we utilize the hierarchical information in hyperbolic space through exponential mapping and logarithmic mapping and obtain the anomaly score by subtracting scores of the positive pairs from the negative pairs via a discriminating process. Finally, extensive experiments on four real-world datasets demonstrate that our approach performs superior over representative baseline approaches.