Rethinking Graph Neural Networks for Anomaly Detection

TL;DR

This paper introduces BWGNN, a novel graph neural network designed to detect anomalies by analyzing spectral shifts in graph data, demonstrating improved performance on large-scale datasets.

Contribution

The paper proposes BWGNN, a spectral and spatial localized band-pass filter GNN that addresses the 'right-shift' spectral phenomenon caused by anomalies.

Findings

BWGNN effectively detects anomalies in large-scale datasets.

Spectral analysis reveals anomalies cause a shift towards high frequencies.

BWGNN outperforms existing methods in anomaly detection accuracy.

Abstract

Graph Neural Networks (GNNs) are widely applied for graph anomaly detection. As one of the key components for GNN design is to select a tailored spectral filter, we take the first step towards analyzing anomalies via the lens of the graph spectrum. Our crucial observation is the existence of anomalies will lead to the `right-shift' phenomenon, that is, the spectral energy distribution concentrates less on low frequencies and more on high frequencies. This fact motivates us to propose the Beta Wavelet Graph Neural Network (BWGNN). Indeed, BWGNN has spectral and spatial localized band-pass filters to better handle the `right-shift' phenomenon in anomalies. We demonstrate the effectiveness of BWGNN on four large-scale anomaly detection datasets. Our code and data are released at https://github.com/squareRoot3/Rethinking-Anomaly-Detection