Anomaly Detection with Dual-Channel Heterogeneous Graph Neural Network Based on Hypersphere Dual Learning

LI Qing; ZHONG Jiang; NI Hang

doi:10.12263/DZXB.20231106

您当前的位置：

首页 >

文章列表页 >

Anomaly Detection with Dual-Channel Heterogeneous Graph Neural Network Based on Hypersphere Dual Learning

PAPERS | 更新时间：2025-12-24

- Anomaly Detection with Dual-Channel Heterogeneous Graph Neural Network Based on Hypersphere Dual Learning
- ACTA ELECTRONICA SINICA Vol. 52, Issue 7, Pages: 2212-2218(2024)
- 作者机构：
  
  1.西北工业大学计算机学院，陕西西安 710072
  2.重庆大学计算机学院，重庆 400044
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(62102316;62171382);Fundamental Research Funds for Central Universities;"14th Five-Year Plan" Shared Information System Equipment Preliminary Research Project(315197202);Aviation Science Foundation(20200051053002)
- DOI：10.12263/DZXB.20231106
  CLC： TP311.1
- Received：28 November 2023，
  
  Revised：2024-05-23，
  
  Published：25 July 2024
- 稿件说明：
移动端阅览
李青, 钟将, 倪航. 基于超球面对偶学习的双通道图异常检测方法[J]. 电子学报, 2024, 52(07): 2212-2218.

LI Qing, ZHONG Jiang, NI Hang. Anomaly Detection with Dual-Channel Heterogeneous Graph Neural Network Based on Hypersphere Dual Learning[J]. Acta Electronica Sinica, 2024, 52(07): 2212-2218.
李青, 钟将, 倪航. 基于超球面对偶学习的双通道图异常检测方法[J]. 电子学报, 2024, 52(07): 2212-2218. DOI：10.12263/DZXB.20231106

LI Qing, ZHONG Jiang, NI Hang. Anomaly Detection with Dual-Channel Heterogeneous Graph Neural Network Based on Hypersphere Dual Learning[J]. Acta Electronica Sinica, 2024, 52(07): 2212-2218. DOI：10.12263/DZXB.20231106

摘要

图异常检测作为一项重要的数据挖掘任务，专注于识别与大多数节点显著偏离的异常节点.随着无监督图神经网络技术的进步，现已开发出了基于密度估计、对抗生成网络等多种高效识别图数据中潜在异常的方法.然而，这些方法更注重无监督图异常检测生成高质量的表征，而往往忽略了图异常的特性.因此，本文提出了一个双通道异构图异常检测模型（Dual-channel Heterogeneous Graph Anomaly Detection，HD-GAD）.其模型基础架构包括双通道的图神经网络：全局子结构感知的图神经网络和局部子结构感知的图神经网络，用于图异常检测捕获全局和局部子结构属性.同时，基于对偶推断引入了多超球体学习目标（Multi-Hypersphere Learning，MHL），从宏观和介观超球体角度，分别测量在整个图/社区结构中偏离的异常节点.HD-GAD模型利用相似度函数EmbSim优化训练目标，以缓解多超球面学习中的模型坍问题.最后，在五种不同的数据集上进行了全面的实验.其AUC（Area Under Curve）值在大多数情况下均超过了0.9，达到了行业领先水平，进一步证明了HD-GAD模型在图异常检测任务上的高效性与性能优势.

Abstract

Graph anomaly detection

as a crucial data mining task

focuses on identifying anomalous nodes that significantly deviate from the majority of the nodes. With the advancement of unsupervised graph neural network techniques

various efficient methods have been developed to detect potential anomalies in graph data

including those based on density estimation and generative adversarial networks. However

these methods often focus on generating high-quality representations for unsupervised graph anomaly detection and tend to overlook the characteristics of graph anomalies. Consequently

this paper proposes a dual-channel heterogeneous graph anomaly detection model (HD-GAD). Its architecture includes two graph neural networks

i.e. a global substructure-aware GNN (Graph Neural Network) and a local substructure-aware GNN

designed to capture global and local substructural properties for graph anomaly detection. Additionally

the model introduces a multi-hypersphere learning (MHL) objective based on dual inference

which measures anomalies deviating from the overall graph/community structure from macro and meso hypersphere perspectives. The HD-GAD model utilizes the similarity function EmbSim to optimize the training objective

mitigating model collapse issues in multi-hypersphere learning. Comprehensive experiments conducted on five different datasets demonstrated that the AUC (Area Under Curve) values exceeded 0.9 in most cases

achieving industry-leading levels and further proving the HD-GAD model's efficiency and performance advantages in graph anomaly detection tasks.

关键词

Keywords

references

GRUBBS F E . Procedures for detecting outlying observations in samples [J ] . Technometrics , 1969 , 11 ( 1 ): 1 - 21 .

金明 , 丁蓉 . 一种联合时域和空域残差的网络异常检测与节点定位方法 [J ] . 电子学报 , 2023 , 51 ( 5 ): 1172 - 1178 .

JIN M , DING R . Detection and localization of outlier nodes in wireless sensor networks via jointing temporal and spatial residuals [J ] . Acta Electronica Sinica , 2023 , 51 ( 5 ): 1172 - 1178 . (in Chinese)

严莉 , 张凯 , 徐浩 , 等 . 基于图注意力机制和Transformer的异常检测 [J ] . 电子学报 , 2022 , 50 ( 4 ): 900 - 908 .

YAN L , ZHANG K , XU H , et al . Abnormal detection based on graph attention mechanisms and Transformer [J ] . Acta Electronica Sinica , 2022 , 50 ( 4 ): 900 - 908 . (in Chinese)

BREUNIG M M , KRIEGEL H P , NG R T , et al . LOF: Identifying density-based local outliers [C ] // Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data . New York : ACM , 2000 : 93 - 104 .

LI J , DANI H , HU X , et al . Radar: Residual analysis for anomaly detection in attributed networks [C ] // International Joint Conferences on Artificial Intelligence . San Francisco : Curran Associates Inc , 2017 : 2152 - 2158 .

ERFANI S M , RAJASEGARAR S , KARUNASEKERA S , et al . High-dimensional and large-scale anomaly detection using a linear one-class SVM with deep learning [J ] . Pattern Recognition , 2016 , 58 ( C ): 121 - 134 .

LIU Y , LI Z , PAN S , et al . Anomaly detection on attributed networks via contrastive self-supervised learning [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2022 , 33 ( 6 ): 2378 - 2392 .

LI Y N , HUANG X , LI J D , et al . SpecAE: Spectral autoencoder for anomaly detection in attributed networks [C ] // Proceedings of the 28th ACM International Conference on Information and Knowledge Management . New York : ACM , 2019 : 2233 - 2236 .

LIU K , DOU Y , ZHAO Y , et al . Bond: Benchmarking unsupervised outlier node detection on static attributed graphs‍ [J ] . Advances in Neural Information Processing Systems , 2022 , 35 : 27021 - 27035 .

DING K Z , LI J D , BHANUSHALI R , et al . Deep anomaly detection on attributed networks [C ] // Proceedings of the 2019 SIAM International Conference on Data Mining . Philadelphia : Society for Industrial and Applied Mathematics , 2019 : 594 - 602 .

FAN H Y , ZHANG F B , LI Z Y . Anomalydae: Dual autoencoder for anomaly detection on attributed networks [C ] // ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) . Piscataway : IEEE , 2020 : 5685 - 5689 .

CHEN Z X , LIU B , WANG M Q , et al . Generative adversarial attributed network anomaly detection [C ] // Proceedings of the 29th ACM International Conference on Information & Knowledge Management . New York : ACM , 2020 : 1989 - 1992 .

WANG X H , JIN B H , DU Y , et al . One-class graph neural networks for anomaly detection in attributed networks‍ [J ] . Neural Computing and Applications , 2021 , 33 ( 18 ): 12073 - 12085 .

ZHOU S , TAN Q Y , XU Z M , et al . Subtractive aggregation for attributed network anomaly detection [C ] // Proceedings of the 30th ACM International Conference on Information & Knowledge Management . New York : ACM , 2021 : 3672 - 3676 .

MA X X , WU J , XUE S , et al . A comprehensive survey on graph anomaly detection with deep learning [J ] . IEEE Transactions on Knowledge and Data Engineering , 2023 , 35 ( 12 ): 12012 - 12038 .

LIU K , DOU Y T , ZHAO Y , et al . BOND: Benchmarking unsupervised outlier node detection on static attributed graphs [J ] . Advances in Neural Information Processing Systems , 2022 , 35 : 27021 - 27035 .

李康和 , 黄震华 . 基于噪声过滤与特征增强的图神经网络欺诈检测方法 [J ] . 电子学报 , 2023 , 51 ( 11 ): 3053 - 3060 .

LI K H , HUANG Z H . Noise filtering and feature enhancement based graph neural network method for fraud detection [J ] . Acta Electronica Sinica , 2023 , 51 ( 11 ): 3053 - 3060 . (in Chinese)

XU X W , YURUK N , FENG Z D , et al . SCAN: A structural clustering algorithm for networks [C ] // Proceedings of the 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining . New York : ACM , 2007 : 824 - 833 .

LUO X X , WU J , BEHESHTI A , et al . ComGA: Community-aware attributed graph anomaly detection [C ] // Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining . New York : ACM , 2022 : 657 - 665 .

ZHOU S , HUANG X , LIU N H , et al . Unseen anomaly detection on networks via multi-hypersphere learning‍ [C ] // Proceedings of the 2022 SIAM International Conference on Data Mining (SDM) . Philadelphia : Society for Industrial and Applied Mathematics , 2022 : 262 - 270 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

CS-ROMF:Efficient Community Search Based on Graph Combinatorial Optimization

Robust Unsupervised Feature Selection with Double Fuzzy Learning

Feature Anomaly Detection and Pseudo-Label Regression for Adversarial Domain Adaptation

RWK-GNN: Fraud Detection for Imbalanced Graphs with Feature Enhancement and Subkernel Decomposition

Related Author

ZHANG An-ran

WANG Xing-fen

ZHAO Yu-han

LI Li-bo

GAO Yun-long

SHI Shu-guang

ZHAO Zhi-xiang

CAO Chao

Related Institution

Hong Kong Baptist University, Hongkong

Beijing Information Science and Technology University

School of Ocean Information Engineering, Jimei University

Third Institute of Oceanography, Ministry of Natural Resources

National Institute for Data Science in Health and Medicine, Xiamen University

⁰