Data augmentation based multi-view contrastive learning graph anomaly detection

LI Yifan; LI Jiayin; LIN Xingpeng; DAI Yuanfei; XU Li

doi:10.11959/j.issn.2096-109x.2024075

您当前的位置：

首页 >

文章列表页 >

Data augmentation based multi-view contrastive learning graph anomaly detection

Papers | 更新时间：2024-12-20

- Data augmentation based multi-view contrastive learning graph anomaly detection
- Chinese Journal of Network and Information Security Vol. 10, Issue 5, Pages: 163-174(2024)
- 作者机构：
  
  1.福建师范大学计算机与网络空间安全学院，福建福州 350000
  2.福建省网络安全与密码技术重点实验室，福建福州 350000
  3.南京工业大学计算机与信息工程学院，江苏南京 210000
- 作者简介：
- 基金信息：
  
  The National Natural Science Foundation of China(62471139;U1905211;62202221);The National Science and Technology Project Record-Centralized Guided Local Science and Technology Development Special Project(2023L3007);The Natural Science Foundation of Jiangsu Province(BK20220331);The Natural Science Foundation of Fujian Province(2023J05128);Science and Technology Projects in Fujian Province(2022G02003)
- DOI：10.11959/j.issn.2096-109x.2024075
  CLC： TP393
- Received：22 April 2024，
  
  Revised：2024-07-19，
  
  Published：25 October 2024
- 稿件说明：
移动端阅览
李一凡, 李家印, 林兴澎, 等. 基于数据增强的多视图对比学习图异常检测[J]. 网络与信息安全学报, 2024, 10(5): 163-174.

Format: LI Y F, LI J Y, LIN X P, et al. Data augmentation based multi-view contrastive learning graph anomaly detection[J]. Chinese Journal of Network and Information Security, 2024, 10(5): 163-174.
李一凡, 李家印, 林兴澎, 等. 基于数据增强的多视图对比学习图异常检测[J]. 网络与信息安全学报, 2024, 10(5): 163-174. DOI： 10.11959/j.issn.2096-109x.2024075.

Format: LI Y F, LI J Y, LIN X P, et al. Data augmentation based multi-view contrastive learning graph anomaly detection[J]. Chinese Journal of Network and Information Security, 2024, 10(5): 163-174. DOI： 10.11959/j.issn.2096-109x.2024075.

摘要

图异常检测在预防金融欺诈、网络入侵等有害事件上具有重要价值。基于对比的异常检测方法尽管能够根据异常节点实例对的不一致性有效挖掘异常信息，避免因采用自编码架构导致模型需要全图训练的弊端，但是现有的大多数基于对比的图异常检测方法仅关注节点-子图的对比模式，忽略了采样的节点-子图实例对中只包含目标节点的局部信息，同时没有考虑各子图对目标节点的重要性，导致节点全局信息缺失和对比模式过于泛化的问题。为解决上述问题，提升图异常检测的准确度，提出了一种基于数据增强的多视图对比学习图异常检测（data augmentation based multi-view contrastive learning graph anomaly detection，DAMC-GAD）方法。具体地，提出了一种用于异常检测的图数据增强方法，通过目标节点的相对局部结构和自身属性关联距离较远的节点，以构建全局信息丰富的增强视图。引入逐层采样结合节点-子图对比，根据子图重要性制定对比模型的优化策略。通过互补的融合策略构建基于数据增强的多视图对比学习模型，在合成异常与真实异常数据集上进行大量实验，实验结果表明，DAMC-GAD在两类数据集上均优于目前先进的基线模型。

Abstract

Graph anomaly detection is valuable in preventing harmful events such as financial fraud and network intrusion. Although contrast-based anomaly detection methods could effectively mine anomaly information based on the inconsistency of anomalous node instance pairs

avoiding the drawback of using self-coding architecture that led to the need for full graph training for the model. However

most existing contrast-based graph anomaly detection methods focused only on node-subgraph contrast patterns

ignoring the fact that the sampled node-subgraph instance pairs contained only the local information of the target node

and at the same time did not take into account the importance of each subgraph to the target node

which led to the lack of global information about the node and the emergence of the problem that the contrast patterns were too generalized. In order to solve the problems mentioned above and to improve the accuracy of graph anomaly detection

a graph anomaly detection by data augmentation and multi-view contrastive learning (DAMC-GAD) was proposed. Specifically

a graph data augmentation method for anomaly detection was proposed

in which the relative local structure of target nodes and their own attributes were used to correlate distant nodes in order to construct an augmented view that was rich in global information. Layer-by-layer sampling combined with node-subgraph contrast was introduced

and optimization strategies for the contrast model were developed based on the importance of the subgraph. A multi-view contrastive learning model with data augmentation was constructed through a complementary fusion strategy

and extensive experiments were conducted on synthetic anomaly and real anomaly datasets

which show that DAMC-GAD outperforms the current state-of-the-art baseline model on both types of datasets.

关键词

Keywords

references

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 .

ZHAO T , JIANG T W , SHAH N , et al . A synergistic approach for graph anomaly detection with pattern mining and feature learning [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2022 , 33 ( 6 ): 2393 - 2405 .

李忠 , 靳小龙 , 庄传志 , 等 . 面向图的异常检测研究综述 [J ] . 软件学报 , 2021 , 32 ( 1 ): 167 - 193 .

LI Z , JIN X L , ZHUANG C Z , et al . Overview on graph based anomaly detection [J ] . Journal of Software , 2021 , 32 ( 1 ): 167 - 193 .

高国鹏 , 房耀东 , 韩彦芳 , 等 . 面向虚假新闻检测的社交媒体多模态数据集构建 [J ] . 网络与信息安全学报 , 2023 , 9 ( 4 ): 144 - 154 .

GAO G P , FANG Y D , HAN Y F , et al . Construction of multi-modal social media dataset for fake news detection [J ] . Chinese Journal of Network and Information Security , 2023 , 9 ( 4 ): 144 - 154 .

GORI M , MONFARDINI G , SCARSELLI F . A new model for learning in graph domains [C ] // Proceedings of 2005 IEEE International Joint Conference on Neural Networks . Piscataway : IEEE Press , 2005 : 729 - 734 .

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

袁非牛 , 章琳 , 史劲亭 , 等 . 自编码神经网络理论及应用综述 [J ] . 计算机学报 , 2019 , 42 ( 1 ): 203 - 230 .

YUAN F N , ZHANG L , SHI J T , et al . Theories and applications of auto-encoder neural networks: a literature survey [J ] . Chinese Journal of Computers , 2019 , 42 ( 1 ): 203 - 230 .

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

SHAO M L , LIN Y J , PENG Q Y , et al . Learning graph deep autoencoder for anomaly detection in multi-attributed networks [J ] . Knowledge-Based Systems , 2023 , 260 : 110084 .

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

LIU Y X , LI Z , PAN S R , 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 .

JIN M , LIU Y , ZHENG Y , et al . Anemone: graph anomaly detection with multi-scale contrastive learning [C ] // Proceedings of the 30th ACM International Conference on Information & Knowledge Management . 2021 : 3122 - 3126 .

DUAN J C , WANG S W , ZHANG P , et al . Graph anomaly detection via multi-scale contrastive learning networks with augmented view [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2023 , 37 ( 6 ): 7459 - 7467 .

ZHUANG Z , TING K M , PANG G S , et al . Subgraph centralization: a necessary step for graph anomaly detection [M ] // Proceedings of the 2023 SIAM International Conference on Data Mining (SDM) . Philadelphia, PA : Society for Industrial and Applied Mathematics , 2023 : 703 - 711 .

TONG H H , FALOUTSOS C , PAN J Y . Fast random walk with restart and its applications [C ] // Proceedings of the Sixth International Conference on Data Mining (ICDM'06) . Piscataway : IEEE Press , 2006 : 613 - 622 .

DING K Z , XU Z , TONG H H , et al . Data augmentation for deep graph learning [J ] . ACM SIGKDD Explorations Newsletter , 2022 , 24 ( 2 ): 61 - 77 .

HAMILTON W L , YING R , LESKOVEC J . Inductive representation learning on large graphs [EB ] . arXiv Preprint arXiv: 1706.02216 , 2017 .

张欣欣 , 许力 , 周赵斌 . 社会网络中基于路径的社团划分方法 [J ] . 福建师范大学学报(自然科学版) , 2023 , 39 ( 2 ): 35 - 40 .

ZHANG X X , XU L , ZHOU Z B . Path-based community detection method in social networks [J ] . Journal of Fujian Normal University (Natural Science Edition) , 2023 , 39 ( 2 ): 35 - 40 .

SÁNCHEZ P I , MÜLLER E , LAFORET F , et al . Statistical selection of congruent subspaces for mining attributed graphs [C ] // Proceedings of the 2013 IEEE 13th International Conference on Data Mining . Piscataway : IEEE Press , 2013 : 647 - 656 .

XU Z M , HUANG X , ZHAO Y , et al . Contrastive attributed network anomaly detection with data augmentation [C ] // Proceedings of Pacific-Asia Conference on Knowledge Discovery and Data Mining . Cham : Springer , 2022 : 444 - 457 .

LI X W , SUN A T , ZHAO M K , et al . Multi-intention oriented contrastive learning for sequential recommendation [C ] // Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining . New York : ACM , 2023 : 411 - 419 .

ZHAO W T , XU G P , CUI Z , et al . Deep graph structural infomax [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2023 , 37 ( 4 ): 4920 - 4928 .

PENG Z , HUANG W B , LUO M N , et al . Graph representation learning via graphical mutual information maximization [EB ] . arXiv Preprint arXiv: 2002.01169 , 2020 .

ZHU Y Q , XU Y C , YU F , et al . Graph contrastive learning with adaptive augmentation [C ] // Proceedings of the Web Conference 2021 . New York : ACM , 2021 : 2069 - 2080 .

THAKOOR S , TALLEC C , AZAR M G , et al . Bootstrapped representation learning on graphs [C ] // Proceedings of ICLR 2021 Workshop on Geometrical and Topological Representation Learning , 2021 .

TOGNINALLI M , GHISU E , LLINARES-LÓPEZ F , et al . Wasserstein weisfeiler-Lehman graph kernels [EB ] . arXiv Preprint arXiv: 1906.01277 , 2019 .

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 .

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 .

PENG Z , LUO M N , LI J D , et al . ANOMALOUS: a joint modeling approach for anomaly detection on attributed networks [C ] // Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence . California : International Joint Conferences on Artificial Intelligence Organization , 2018 : 3513 - 3519 .

LIU F Z , MA X X , WU J , et al . DAGAD: data augmentation for graph anomaly detection [C ] // Proceedings of the 2022 IEEE International Conference on Data Mining (ICDM) . Piscataway : IEEE Press , 2022 : 259 - 268 .

LI X , XIAO C J , FENG Z L , et al . Controlled graph neural networks with denoising diffusion for anomaly detection [J ] . Expert Systems with Applications , 2024 , 237 : 121533 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

DynaSynth: a large language model fine-tuning data dynamic synthesis agent tool for unstructured cybersecurity corpus

Gate-level hardware trojan detection method based on graph Transformer

Research progress on detection of software vulnerabilities based on code similarity

Multi-query based key node mining algorithm for social networks

Pseudo-siamese network image tampering localization model based on reinforced samples

Related Author

Zhao Zhengyang

Li Siqi

Zhao Bofu

Wang Buhong

Piao Chengkai

Guan Yongjian

Zheng Rui

Yu Hong

Related Institution

Information and Navigation College, Air Force Engineering University

Information Engineering University

Engineering Research Center of Digital Forensics, Ministry of Education, Nanjing University of Information Science and Technology

Department of Computer Science, Nanjing University of Information Science and Technology

Department of Cyberspace Security, Nanjing University of Information Science and Technology

⁰