Unsupervised graph-level anomaly detection (UGAD) has garnered increasing attention in recent years due to its significance. However, most existing methods only rely on traditional graph neural networks to explore pairwise relationships but such kind of pairwise edges are not enough to describe multifaceted relationships involving anomaly. There is an emergency need to exploit node group information which plays a crucial role in UGAD. In addition, most previous works ignore the global underlying properties (e.g., hierarchy and power-law structure) which are common in real-world graph datasets and therefore are indispensable factors on 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 node group connections, we construct hypergraphs based on 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 hyperboloid model. To the best of our knowledge, this is the first work to simultaneously apply hypergraph with node group connections and hyperbolic geometry into this field. Extensive experiments on several real world datasets of different fields demonstrate the superiority of HC-GLAD on UGAD task. The code is available at https://github.com/Yali-F/HC-GLAD.

翻译：近年来，无监督图级异常检测因其重要性而受到越来越多的关注。然而，现有方法大多仅依赖传统图神经网络来探索成对关系，但此类成对边不足以描述涉及异常的多方面关联。迫切需要利用在无监督图级异常检测中起关键作用的节点群组信息。此外，先前工作大多忽略了现实图数据集中普遍存在的全局内在属性（如层次结构与幂律结构），而这些属性正是无监督图级异常检测任务中不可或缺的因素。本文提出一种面向无监督图级异常检测的新型双曲双路对比学习方法（简称HC-GLAD）。为挖掘节点群组连接，我们基于黄金模体构建超图并执行超图卷积。进一步地，为保持现实图数据的层次特性，我们首次将双曲几何引入该领域，并基于双曲面模型在双曲空间中同时进行图与超图的嵌入学习。据我们所知，这是首个将包含节点群组连接的超图与双曲几何同时应用于该领域的研究。在多个不同领域的现实数据集上的大量实验验证了HC-GLAD在无监督图级异常检测任务上的优越性。代码公开于https://github.com/Yali-F/HC-GLAD。