arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.09535cs.LGcs.SI
收藏

基于无监督GNNs的图异常检测

Graph Anomaly Detection with Unsupervised GNNs

Carnegie Mellon University(卡内基梅隆大学);SoundHound(声猎犬)

Lingxiao Zhao, Saurabh Sawlani, Arvind Srinivasan, Leman Akoglu

摘要:

基于图的异常检测在现实世界中有着广泛的应用。因此,由于深度学习和图神经网络(GNN)的进步,最近已经转向深度检测模型的主题存在大量文献。绝大多数现有的工作集中在检测单个图中的节点/边/子图异常,而在图数据库中的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)设计GLAM,一种基于GNN的端到端图级异常检测模型,以及(2)专注于无监督模型选择,由于缺乏任何标签,这是众所周知的困难,但对于具有一长串超参数的基于深度NN的模型来说尤其重要。此外,我们提出了一种新的池化策略,称为MMD池化,这是面向检测分布异常,以前没有考虑过。通过对15个真实世界数据集的广泛实验,我们表明:(i)GLAM优于节点级和两阶段(即不是端到端)基线,(ii)模型选择选择比预期(即平均值)更有效的模型-不使用任何标签-在性能变化较大的候选人中。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑