GRASPED: Graph Anomaly Detection using Autoencoder with Spectral Encoder and Decoder (Full Version)

TL;DR

GRASPED is an unsupervised graph anomaly detection model that uses spectral graph wavelet convolution and deconvolution to capture multi-scale information, outperforming existing methods on real-world datasets.

Contribution

It introduces a novel spectral autoencoder with wavelet-based encoder and Wiener deconvolution decoder for effective node anomaly detection.

Findings

Outperforms state-of-the-art models on multiple datasets

Captures multi-scale global and local graph information

Effectively detects anomalies without labeled data

Abstract

Graph machine learning has been widely explored in various domains, such as community detection, transaction analysis, and recommendation systems. In these applications, anomaly detection plays an important role. Recently, studies have shown that anomalies on graphs induce spectral shifts. Some supervised methods have improved the utilization of such spectral domain information. However, they remain limited by the scarcity of labeled data due to the nature of anomalies. On the other hand, existing unsupervised learning approaches predominantly rely on spatial information or only employ low-pass filters, thereby losing the capacity for multi-band analysis. In this paper, we propose Graph Autoencoder with Spectral Encoder and Spectral Decoder (GRASPED) for node anomaly detection. Our unsupervised learning model features an encoder based on Graph Wavelet Convolution, along with structural and attribute decoders. The Graph Wavelet Convolution-based encoder, combined with a Wiener Graph Deconvolution-based decoder, exhibits bandpass filter characteristics that capture global and local graph information at multiple scales. This design allows for a learning-based reconstruction of node attributes, effectively capturing anomaly information. Extensive experiments on several real-world graph anomaly detection datasets demonstrate that GRASPED outperforms current state-of-the-art models.