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

2025-08-21

AI Summary

Existing unsupervised graph node anomaly detection methods struggle to capture multi-spectral features, while supervised approaches are hindered by severe label scarcity. To address these limitations, this paper proposes a spectral-domain-driven unsupervised graph autoencoder. Its core innovation lies in the first integration of graph wavelet convolution and Wiener graph deconvolution into an encoder-decoder architecture endowed with band-pass filtering properties, enabling simultaneous multi-scale local-global feature extraction and spectral multi-band analysis. The model jointly optimizes attribute reconstruction and structural reconstruction objectives, thereby eliminating reliance on either spatial neighborhood aggregation or low-pass spectral smoothing alone. Extensive experiments on multiple real-world graph benchmarks demonstrate significant improvements over state-of-the-art methods, validating both effectiveness and robustness.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Web Mining and Content Analysis: Bridging structured and unstructured 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.

Problem

• Detecting node anomalies in graphs unsupervised
• Overcoming spectral information loss in existing methods
• Addressing labeled data scarcity for graph anomalies

Innovation

• Unsupervised graph autoencoder with spectral encoder
• Graph wavelet convolution for multi-scale analysis
• Wiener deconvolution decoder for anomaly detection