Chi-Square Wavelet Graph Neural Networks for Heterogeneous Graph Anomaly Detection

TL;DR

This paper introduces ChiGAD, a spectral GNN framework utilizing Chi-Square wavelet filters to effectively detect anomalies in heterogeneous graphs, addressing challenges of heterogeneity, high-frequency content, and class imbalance.

Contribution

The paper proposes a novel Chi-Square filter-based spectral GNN framework for heterogeneous graph anomaly detection, improving upon existing methods by capturing diverse signals and handling class imbalance.

Findings

ChiGAD outperforms state-of-the-art models on multiple datasets.

The homogeneous variant ChiGNN performs well on GAD tasks.

Chi-Square filters effectively capture anomalous information across meta-paths.

Abstract

Graph Anomaly Detection (GAD) in heterogeneous networks presents unique challenges due to node and edge heterogeneity. Existing Graph Neural Network (GNN) methods primarily focus on homogeneous GAD and thus fail to address three key issues: (C1) Capturing abnormal signal and rich semantics across diverse meta-paths; (C2) Retaining high-frequency content in HIN dimension alignment; and (C3) Learning effectively from difficult anomaly samples with class imbalance. To overcome these, we propose ChiGAD, a spectral GNN framework based on a novel Chi-Square filter, inspired by the wavelet effectiveness in diverse domains. Specifically, ChiGAD consists of: (1) Multi-Graph Chi-Square Filter, which captures anomalous information via applying dedicated Chi-Square filters to each meta-path graph; (2) Interactive Meta-Graph Convolution, which aligns features while preserving high-frequency information and incorporates heterogeneous messages by a unified Chi-Square Filter; and (3) Contribution-Informed Cross-Entropy Loss, which prioritizes difficult anomalies to address class imbalance. Extensive experiments on public and industrial datasets show that ChiGAD outperforms state-of-the-art models on multiple metrics. Additionally, its homogeneous variant, ChiGNN, excels on seven GAD datasets, validating the effectiveness of Chi-Square filters. Our code is available at https://github.com/HsipingLi/ChiGAD.