Graph-level anomaly detection aims to identify anomalous graphs from a collection of graphs in an unsupervised manner. A common assumption of anomaly detection is that a reasonable decision boundary has a hypersphere shape, but may appear some non-conforming phenomena in high dimensions. Towards this end, we firstly propose a novel deep graph-level anomaly detection model, which learns the graph representation with maximum mutual information between substructure and global structure features while exploring a hypersphere anomaly decision boundary. The idea is to ensure the training data distribution consistent with the decision hypersphere via an orthogonal projection layer. Moreover, we further perform the bi-hypersphere compression to emphasize the discrimination of anomalous graphs from normal graphs. Note that our method is not confined to graph data and is applicable to anomaly detection of other data such as images. The numerical and visualization results on benchmark datasets demonstrate the effectiveness and superiority of our methods in comparison to many baselines and state-of-the-arts.

翻译：图级异常检测旨在以无监督方式从图集合中识别异常图。异常检测的一个常见假设是合理的决策边界呈现超球面形状，但在高维空间中可能会出现一些不一致现象。为此，我们首先提出一种新型深度图级异常检测模型，该模型在探索超球面异常决策边界的同时，通过子结构与全局结构特征间的最大互信息学习图表示。其核心思想是通过正交投影层确保训练数据分布与决策超球面一致。此外，我们进一步实施双超球面压缩以增强异常图与正常图的区分能力。值得注意的是，本方法不仅限于图数据，还可适用于图像等其他数据的异常检测。在基准数据集上的数值与可视化结果表明，与诸多基线及前沿方法相比，我们的方法具有有效性和优越性。