论文标题
与无监督的GNN的图形异常检测
Graph Anomaly Detection with Unsupervised GNNs
论文作者
论文摘要
基于图的异常检测在现实世界中发现了许多应用。因此，由于深度学习和图形神经网络（GNN）的进步，有关该主题最近朝着深层检测模型转向的大量文献。绝大多数先前的工作都集中在单个图中检测节点/边缘/子图异常，在图数据库中，在图级异常检测方面的工作要少得多。这项工作旨在填补文献中的两个空白：我们（1）Design Glam，一种基于GNN的端到端的图形异常检测模型，（2）专注于无监督的模型选择，众所周知，由于缺乏任何标签，但对于具有长期NN模型而言尤其重要，但对于具有长期的超级参数列表而言，这尤其是至关重要的。此外，我们提出了一种用于图形嵌入的新的合并策略，称为MMD释放，该策略旨在检测以前未考虑的分布异常。通过对15个现实世界数据集进行的大量实验，我们表明（i）优于节点级别和两个阶段（即不是端到端）基准的基准，（ii）模型选择的模型比预期（即平均）更有效的模型（即，在表现方面具有较大的候选者中都没有使用任何Labels）。
Graph-based anomaly detection finds numerous applications in the real-world. Thus, there exists extensive literature on the topic that has recently shifted toward deep detection models due to advances in deep learning and graph neural networks (GNNs). A vast majority of prior work focuses on detecting node/edge/subgraph anomalies within a single graph, with much less work on graph-level anomaly detection in a graph database. This work aims to fill two gaps in the literature: We (1) design GLAM, an end-to-end graph-level anomaly detection model based on GNNs, and (2) focus on unsupervised model selection, which is notoriously hard due to lack of any labels, yet especially critical for deep NN based models with a long list of hyper-parameters. Further, we propose a new pooling strategy for graph-level embedding, called MMD-pooling, that is geared toward detecting distribution anomalies which has not been considered before. Through extensive experiments on 15 real-world datasets, we show that (i) GLAM outperforms node-level and two-stage (i.e. not end-to-end) baselines, and (ii) model selection picks a significantly more effective model than expectation (i.e. average) -- without using any labels -- among candidates with otherwise large variation in performance.
