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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Xiping, Dong, Xiangyu, Zhang, Xingyi, Xie, Kun, Feng, Yuanhao, Wang, Bo, Li, Guilin, Zeng, Wuxiong, Shu, Xiujun, Wang, Sibo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908378831257600
author Li, Xiping
Dong, Xiangyu
Zhang, Xingyi
Xie, Kun
Feng, Yuanhao
Wang, Bo
Li, Guilin
Zeng, Wuxiong
Shu, Xiujun
Wang, Sibo
author_facet Li, Xiping
Dong, Xiangyu
Zhang, Xingyi
Xie, Kun
Feng, Yuanhao
Wang, Bo
Li, Guilin
Zeng, Wuxiong
Shu, Xiujun
Wang, Sibo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_18934
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Chi-Square Wavelet Graph Neural Networks for Heterogeneous Graph Anomaly Detection
Li, Xiping
Dong, Xiangyu
Zhang, Xingyi
Xie, Kun
Feng, Yuanhao
Wang, Bo
Li, Guilin
Zeng, Wuxiong
Shu, Xiujun
Wang, Sibo
Machine Learning
Artificial Intelligence
Information Retrieval
Social and Information Networks
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.
title Chi-Square Wavelet Graph Neural Networks for Heterogeneous Graph Anomaly Detection
topic Machine Learning
Artificial Intelligence
Information Retrieval
Social and Information Networks
url https://arxiv.org/abs/2505.18934