Graph-level anomaly detection aims to identify abnormal graphs that exhibit deviant structures and node attributes compared to the majority in a graph set. One primary challenge is to learn normal patterns manifested in both fine-grained and holistic views of graphs for identifying graphs that are abnormal in part or in whole. To tackle this challenge, we propose a novel approach called Hierarchical Memory Networks (HimNet), which learns hierarchical memory modules -- node and graph memory modules -- via a graph autoencoder network architecture. The node-level memory module is trained to model fine-grained, internal graph interactions among nodes for detecting locally abnormal graphs, while the graph-level memory module is dedicated to the learning of holistic normal patterns for detecting globally abnormal graphs. The two modules are jointly optimized to detect both locally- and globally-anomalous graphs. Extensive empirical results on 16 real-world graph datasets from various domains show that i) HimNet significantly outperforms the state-of-art methods and ii) it is robust to anomaly contamination. Codes are available at: https://github.com/Niuchx/HimNet.

翻译：图级异常检测旨在识别与图集中大多数图相比具有异常结构和节点属性的异常图。其核心挑战在于从图的细粒度与整体视角同时学习正常模式，以识别部分异常或整体异常的图。为解决此挑战，我们提出一种名为层级记忆网络(Hierarchical Memory Networks, HimNet)的新方法，该方法通过图自编码器网络架构学习层级记忆模块——节点记忆模块和图记忆模块。节点级记忆模块用于建模节点间细粒度的内部图交互，以检测局部异常图；而图级记忆模块则专门学习整体正常模式，以检测全局异常图。两个模块通过联合优化，实现局部异常图与全局异常图的共同检测。在来自不同领域的16个真实图数据集上的大量实验结果表明：(i) HimNet显著优于现有最优方法；(ii) 该方法对异常污染具有鲁棒性。代码已开源：https://github.com/Niuchx/HimNet。