HC-GLAD: Dual Hyperbolic Contrastive Learning for Unsupervised Graph-Level Anomaly Detection

TL;DR

This paper introduces HC-GLAD, a novel unsupervised graph-level anomaly detection method that leverages hypergraph convolution and hyperbolic geometry to capture high-order dependencies and hierarchical properties in real-world graphs.

Contribution

It is the first to combine hypergraph-based high-order node interactions with hyperbolic geometry for improved anomaly detection in graphs.

Findings

HC-GLAD outperforms existing methods on 13 real-world datasets.

Hypergraph convolution captures high-order node group information effectively.

Hyperbolic embedding preserves graph hierarchy and power-law structures.

Abstract

Unsupervised graph-level anomaly detection (UGAD) has garnered increasing attention in recent years due to its significance. Most existing methods that rely on traditional GNNs mainly consider pairwise relationships between first-order neighbors, which is insufficient to capture the complex high-order dependencies often associated with anomalies. This limitation underscores the necessity of exploring high-order node interactions in UGAD. In addition, most previous works ignore the underlying properties (e.g., hierarchy and power-law structure) which are common in real-world graph datasets and therefore are indispensable factors in the UGAD task. In this paper, we propose a novel Dual Hyperbolic Contrastive Learning for Unsupervised Graph-Level Anomaly Detection (HC-GLAD in short). To exploit high-order node group information, we construct hypergraphs based on pre-designed gold motifs and subsequently perform hypergraph convolution. Furthermore, to preserve the hierarchy of real-world graphs, we introduce hyperbolic geometry into this field and conduct both graph and hypergraph embedding learning in hyperbolic space with the hyperboloid model. To the best of our knowledge, this is the first work to simultaneously apply hypergraph with node group information and hyperbolic geometry in this field. Extensive experiments on 13 real-world datasets of different fields demonstrate the superiority of HC-GLAD on the UGAD task. The code is available at https://github.com/Yali-F/HC-GLAD.