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

• URL: http://arxiv.org/abs/2505.18934v1
• Date: Sun, 25 May 2025 01:58:02 GMT
• Title: Chi-Square Wavelet Graph Neural Networks for Heterogeneous Graph Anomaly Detection
• Abstract summary: Existing Graph Neural Network (GNN) methods primarily focus on homogeneous Graph Anomaly Detection (GAD)<n>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.
• Score: 14.15596277485716
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Feature Transformation Enhanced Jacobi Polynomial Graph Filtering for Graph Anomaly Detection [17.594530405168445]
  Graph anomaly detection (GAD) based on frequency-domain filtering have achieved promising results.<n>Existing approaches face three major challenges: First, they use static basic function to constructed graph filter.<n>Second, they fail to adequately consider the importance information of each attribute in the node feature vector.<n>Third, they utilize node labels for GAD, leading to the loss of fine-grained information.
  arXiv  Detail & Related papers  (2026-08-27T13:57:09Z)
• Generative Diffusion Models of Stochastic Graph Signals [74.4097723209053]
  This paper tackles problems of conditional graph signal generative modeling and tackles them with a single denoising diffusion framework.<n>We learn a reverse diffusion process, parametrized by graph neural networks (GNNs), that draws graph signals conditioned directly on the graph topology and on node-feature side information.<n>We demonstrate our method on two generative tasks: stock price forecasting and optimal wireless resource allocation, with extensive numerical results in both domains.
  arXiv  Detail & Related papers  (2026-07-07T22:02:13Z)
• Hierarchical Multi-Scale Graph Neural Networks: Scalable Heterophilous Learning with Oversmoothing and Oversquashing Mitigation [0.0]
  Hierarchical Multi-view HAAR (HMH) is a novel graph-learning framework that scales in near-linear time.<n>HMH outperforms state-of-the-art spectral baselines, achieving up to a 3% improvement on node classification and 7% points on graph classification datasets.
  arXiv  Detail & Related papers  (2026-05-08T22:35:17Z)
• Multi-Head Spectral-Adaptive Graph Anomaly Detection [7.788514265469946]
  Graph anomaly detection has broad applications in financial fraud and risk control.<n>Existing graph anomaly detection methods often face significant challenges when dealing with complex and variable abnormal patterns.<n>We propose a Multi-Head Spectral-Adaptive Graph Neural Network (MHSA-GNN)<n>Our method effectively preserves high-frequency abnormal signals and significantly outperforms existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-12-25T14:55:43Z)
• Addressing Graph Anomaly Detection via Causal Edge Separation and Spectrum [6.722106415172189]
  In the real world, anomalous entities often add more legitimate connections while hiding direct links with other anomalous entities.<n>This study analyzes the spectral distribution of nodes with different heterophilic degrees and discovers that the heterophily of anomalous nodes causes the spectral energy to shift.<n>We propose a spectral neural network CES2-GAD based on causal edge separation for anomaly detection on heterophilic graphs.
  arXiv  Detail & Related papers  (2025-08-20T12:59:22Z)
• Collaborative Filtering Meets Spectrum Shift: Connecting User-Item Interaction with Graph-Structured Side Information [11.650613484855356]
  Graph Neural Networks (GNNs) have demonstrated their superiority in collaborative filtering.<n>However, when graph-structured side information is integrated into the U-I bipartite graph, existing graph collaborative filtering methods fall short of achieving satisfactory performance.<n>We propose Spectrum Shift Correction (dubbed SSC), incorporating shifting and scaling factors to enable spectral GNNs to adapt to the shifted spectrum.
  arXiv  Detail & Related papers  (2025-02-12T02:24:26Z)
• Dual-Frequency Filtering Self-aware Graph Neural Networks for Homophilic and Heterophilic Graphs [60.82508765185161]
  We propose Dual-Frequency Filtering Self-aware Graph Neural Networks (DFGNN) DFGNN integrates low-pass and high-pass filters to extract smooth and detailed topological features. It dynamically adjusts filtering ratios to accommodate both homophilic and heterophilic graphs.
  arXiv  Detail & Related papers  (2024-11-18T04:57:05Z)
• Addressing Graph Heterogeneity and Heterophily from A Spectral Perspective [46.37860909753809]
  Heterogeneity refers to a graph with multiple types of nodes or edges, while heterophily refers to the fact that connected nodes are more likely to have dissimilar attributes or labels.<n>We propose a Heterogeneous Heterophilic Spectral Graph Neural Network (H2SGNN), which employs two modules: local independent filtering and global hybrid filtering.<n> Extensive experiments are conducted on four datasets to validate the effectiveness of the proposed H2SGNN.
  arXiv  Detail & Related papers  (2024-10-17T09:23:53Z)
• Spectral Greedy Coresets for Graph Neural Networks [61.24300262316091]
  The ubiquity of large-scale graphs in node-classification tasks hinders the real-world applications of Graph Neural Networks (GNNs) This paper studies graph coresets for GNNs and avoids the interdependence issue by selecting ego-graphs based on their spectral embeddings. Our spectral greedy graph coreset (SGGC) scales to graphs with millions of nodes, obviates the need for model pre-training, and applies to low-homophily graphs.
  arXiv  Detail & Related papers  (2024-05-27T17:52:12Z)
• GPatcher: A Simple and Adaptive MLP Model for Alleviating Graph Heterophily [15.93465948768545]
  We demystify the impact of graph heterophily on graph neural networks (GNNs) filters. We propose a simple yet powerful GNN named GPatcher by leveraging the patch-Mixer architectures. Our model demonstrates outstanding performance on node classification compared with popular homophily GNNs and state-of-the-art heterophily GNNs.
  arXiv  Detail & Related papers  (2023-06-25T20:57:35Z)
• Skeleton-Parted Graph Scattering Networks for 3D Human Motion Prediction [120.08257447708503]
  Graph convolutional network based methods that model the body-joints' relations, have recently shown great promise in 3D skeleton-based human motion prediction. We propose a novel skeleton-parted graph scattering network (SPGSN) SPGSN outperforms state-of-the-art methods by remarkable margins of 13.8%, 9.3% and 2.7% in terms of 3D mean per joint position error (MPJPE) on Human3.6M, CMU Mocap and 3DPW datasets, respectively.
  arXiv  Detail & Related papers  (2022-07-31T05:51:39Z)
• Deep Graph-level Anomaly Detection by Glocal Knowledge Distillation [61.39364567221311]
  Graph-level anomaly detection (GAD) describes the problem of detecting graphs that are abnormal in their structure and/or the features of their nodes. One of the challenges in GAD is to devise graph representations that enable the detection of both locally- and globally-anomalous graphs. We introduce a novel deep anomaly detection approach for GAD that learns rich global and local normal pattern information by joint random distillation of graph and node representations.
  arXiv  Detail & Related papers  (2021-12-19T05:04:53Z)
• Message Passing in Graph Convolution Networks via Adaptive Filter Banks [81.12823274576274]
  We present a novel graph convolution operator, termed BankGCN. It decomposes multi-channel signals on graphs into subspaces and handles particular information in each subspace with an adapted filter. It achieves excellent performance in graph classification on a collection of benchmark graph datasets.
  arXiv  Detail & Related papers  (2021-06-18T04:23:34Z)
• Graph Neural Networks with Adaptive Frequency Response Filter [55.626174910206046]
  We develop a graph neural network framework AdaGNN with a well-smooth adaptive frequency response filter. We empirically validate the effectiveness of the proposed framework on various benchmark datasets.
  arXiv  Detail & Related papers  (2021-04-26T19:31:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.