Can I read One-class Graph Neural Networks for Anomaly Detection in Attributed Networks on EtoBox?

One-class Graph Neural Networks for Anomaly Detection in Attributed Networks by Xuhong Wang; Baihong Jin; Ying Du; Ping Cui; Yingshui Tan; Yupu Yang is a Computer Science article available to read on EtoBox.

What is One-class Graph Neural Networks for Anomaly Detection in Attributed Networks about?

Nowadays, graph-structured data are increasingly used to model complex systems. Meanwhile, detecting anomalies from graph has become a vital research problem of pressing societal concerns. Anomaly detection is an unsupervised learning task of identifying rare data that differ from the majority. As one of the dominant anomaly detection algorithms, one-class support vector machine has been widely used to detect outliers. However, those traditional anomaly detection methods lost their effectiveness in graph data. Since traditional anomaly detection methods are stable, robust and easy to use, it is vitally important to generalize them to graph data. In this work, we propose one-class graph neural network (OCGNN), a one-class classification framework for graph anomaly detection. OCGNN is designed to combine the powerful representation ability of graph neural networks along with the classical one-class objective. Compared with other baselines, OCGNN achieves significant improvements in extensive experiments.

Who reads One-class Graph Neural Networks for Anomaly Detection in Attributed Networks?

Author

Xuhong Wang; Baihong Jin; Ying Du; Ping Cui; Yingshui Tan; Yupu Yang

Publisher

Springer Science and Business Media LLC

Published

2021

Language

EN

Field

Computer Science (Physical Sciences)