检索结果-内蒙古大学图书馆

graph anomaly detection via Multiscale Contrastive Self-Supervised Learning From Local to Global

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS 2025年第2期12卷 485-497页

作者： Wang, Xiaofeng Lai, Shuaiming Zhu, Shuailei Chen, Yuntao Lv, Laishui Qi, Yuanyuan China Jiliang Univ Sch Informat Engn Hangzhou 310018 Peoples R China

graph anomaly detection is a challenging task in graph data mining, aiming to recognize unconventional patterns within a network. Recently, there has been increasing attention on graph anomaly detection based on contrastive learning due to its high adaptability to the sample imbalance problem. However, most existing work typically focuses on the contrast of local views while neglecting global comparison information, leading to suboptimal performance. To address this issue, we introduce a new multiscale contrastive self-supervised learning framework for graph anomaly detection (GADMCLG). Our approach incorporates local-level contrasts involving node-node and node- subgraph contrast, and global-level subgraph-subgraph contrast. The former mines localized abnormal information, while the latter is intended to capture global anomalous patterns. Specifically, our proposed subgraph-subgraph contrast adopts the h-order neighbor subgraph sampling instead of augmented subgraphs through edge perturbation. This sampling strategy ensures a comprehensive observation of the neighborhood surrounding the target node, thereby mitigating the introduction of extraneous noise and providing interpretability for the detected results. Furthermore, we incorporate a subgraph centralization technique to reduce the bias caused by the absolute position of subgraphs in the attribute space, which enhances the model's ability to identify anomalies at different scales. Extensive experimental results on six real-world datasets demonstrate the effectiveness of our method and its superiority compared with state-of-the-art approaches.

关键词： Contrastive learning Contrastive learning graph anomaly detection graph anomaly detection multiscale framework multiscale framework subgraph centralization subgraph centralization subgraph sampling subgraph sampling

来源：评论

学校读者我要写书评

暂无评论

graph anomaly detection based on hybrid node representation learning

引用

NEURAL NETWORKS 2025年 185卷 107169页

作者： Wang, Xiang Dou, Hao Dong, Dibo Meng, Zhenyu Fujian Univ Technol Inst Artificial Intelligence Fuzhou Peoples R China Fujian Univ Technol Fujian Prov Key Lab Big Data Min & Applicat Fuzhou Peoples R China Fujian Univ Technol Inst Smart Marine & Engn Fuzhou 350118 Peoples R China

anomaly detection on graph data has garnered significant interest from both the academia and industry. In recent years, fueled by the rapid development of graph Neural Networks (GNNs), various GNNs-based anomaly detection methods have been proposed and achieved good results. However, GNNs-based methods assume that connected nodes have similar classes and features, leading to issues of class inconsistency and semantic inconsistency in graph anomaly detection. Existing methods have yet to adequately address these issues, thereby limiting the detection performance of the model. Therefore, an anomaly detection method that consists of one semantic fusion-based node representation module and one attention mechanism-based node representation module is proposed to resolve the aforementioned issues, respectively. The main highlights of the current study are outlined below: First, a novel framework is developed, aiming to better resolve the issues of class inconsistency and semantic inconsistency in graph anomaly detection. Second, we propose the semantic fusion-based node representation module which is based on Chebyshev polynomial graph filtering and is able to effectively capture high-frequency and low-frequency components of graph signals. Third, to overcome semantic inconsistency in graph data, we devise an attention mechanism-based node representation module which can adaptively learns importance information of graph nodes, resulting in significant improvement of the model performance. Finally, experiments are carried out on five real-world anomaly detection datasets, and the results show that the proposed method outperforms the state-of-the-art methods.

关键词： Attention mechanism Attributed graph graph anomaly detection graph filtering graph neural networks

来源：评论

学校读者我要写书评

暂无评论

graph anomaly detection via Multi-View Discriminative Awareness Learning

引用

IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING 2024年第6期11卷 6623-6635页

作者： Lian, Jie Wang, Xuzheng Lin, Xincan Wu, Zhihao Wang, Shiping Guo, Wenzhong Fuzhou Univ Coll Comp & Data Sci Fuzhou 350108 Peoples R China Fuzhou Univ Fujian Prov Key Lab Network Comp & Intelligent Inf Fuzhou 350108 Peoples R China

With the deeper research on attributed networks, graph anomaly detection is becoming an increasingly important topic. It aims to identify patterns deviating from a majority of nodes. Currently, graph anomaly detection algorithms based on reconstruction-based learning and contrastive-based learning have gained significant attention. To harness diverse supervised signals, an intuitive approach is to find an elegant strategy to fuse these two paradigms, forming the hybrid learning paradigm. Despite the success of the hybrid learning paradigm, due to its subgraph sampling based approach, it still grapples with issues related to unreliable neighborhood information and the neglect of topological details. To address these limitations, this paper proposes a new hybrid learning paradigm via multi-view discriminative awareness learning for graph anomaly detection. Unlike the previous hybrid learning paradigm, the graph reconstruction module fully incorporates attribute and topology information, enhancing the comprehensiveness of data reconstruction. Moreover, the multi-view discrimination module employs a view-level contrast method based on the complete graph, which helps to comprehensively extract the information in the attributed network and mitigates the neighborhood unreliability without increasing the complexity. The experimental results, obtained from a rigorous evaluation on six benchmark datasets, demonstrate the effectiveness of the proposed method compared to existing baseline methods.

关键词： anomaly detection Hybrid learning Topology Network topology Contrastive learning Complexity theory Computational modeling Attributed networks graph anomaly detection graph neural networks self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

graph anomaly detection with Few Labels: A Data-Centric Approach 24

Graph Anomaly Detection with Few Labels: A Data-Centric Appr...

引用

30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

作者： Ma, Xiaoxiao Li, Ruikun Liu, Fanzhen Ding, Kaize Yang, Jian Wu, Jia Macquarie Univ Sch Comp Sydney NSW Australia Univ Sydney Business Sch Sydney NSW Australia Northwestern Univ Dept Stat & Data Sci Evanston IL USA

ISBN: (纸本)9798400704901

Anomalous node detection in a static graph faces significant challenges due to the rarity of anomalies and the substantial cost of labeling their deviant structure and attribute patterns. These challenges give rise to data-centric problems, including extremely imbalanced data distributions and intricate graph learning, which significantly impede machine learning and deep learning methods from discerning the patterns of graph anomalies with few labels. While these issues remain crucial, much of the current research focuses on addressing the induced technical challenges, treating the shortage of labeled data as a given. Distinct from previous efforts, this work focuses on tackling the data-centric problems by generating auxiliary training nodes that conform to the original graph topology and attribute distribution. We categorize this approach as 'data-centric,' aiming to enhance existing anomaly detectors by training them on our synthetic data. However, the methods for generating nodes and the effectiveness of utilizing synthetic data for graph anomaly detection remain unexplored in the realm. To answer these questions, we thoroughly investigate the denoising diffusion model. Drawing from our observations on the diffusion process, we illuminate the shifts in graph energy distribution and establish two principles for designing denoising neural networks tailored to graph anomaly generation. From the insights, we propose a diffusion-based graph generation method to synthesize training nodes, which can be promptly integrated to work with existing anomaly detectors. The empirical results on eight widely-used datasets demonstrate our generated data can effectively enhance the nine state-of-the-art graph detectors' performance.

关键词： graph anomaly detection Generative graph Diffusion

来源：评论

学校读者我要写书评

暂无评论

graph anomaly detection with Adaptive Node Mixup 24

Graph Anomaly Detection with Adaptive Node Mixup

引用

33rd ACM International Conference on Information and Knowledge Management (CIKM)

作者： Zhou, Qinghai Chen, Yuzhong Xu, Zhe Wu, Yuhang Pan, Menghai Das, Mahashweta Yang, Hao Tong, Hanghang Univ Illinois Urbana IL 61801 USA Visa Res Foster City CA USA Meta Platforms Inc Menlo Pk CA USA

ISBN: (纸本)9798400704369

graph anomaly detection (GAD) aims to find network elements (e.g., nodes, edges) with significantly atypical patterns and has a profound impact in a variety of application domains, including social network analysis, security, Web, finance, and many more. Most of the existing methods have been developed in an unsupervised manner or with extremely limited supervision, due to the high cost of acquiring ground-truth information. Consequently, the identified anomalies may turn out to be noises or uneventful instances because of the lack of prior knowledge on graph anomalies. To address the data scarcity issue in GAD, in this paper, we propose, gADAM, a novel graph neural network-based GAD framework, which consolidates (1) an innovative mixup approach to augment the original training data by adaptively interpolating data instances in the embedding space, and (2) an efficacious sampling method to obtain high-quality negative samples for model training. Additionally, to advance the representation learning for GAD, we further equip the proposed framework with a generic prototype-based learning module. Through extensive empirical evaluations, we corroborate the superiority of the proposed gADAM framework on graph anomaly detection w.r.t. various metrics.

关键词： graph anomaly detection augmentation mixup

来源：评论

学校读者我要写书评

暂无评论

graph anomaly detection With graph Neural Networks: Current Status and Challenges

引用

IEEE ACCESS 2022年 10卷 111820-111829页

作者： Kim, Hwan Lee, Byung Suk Shin, Won-Yong Lim, Sungsu Chungnam Natl Univ Dept Comp Sci & Engn Daejeon 34134 South Korea Univ Vermont Dept Comp Sci Burlington VT 05405 USA Yonsei Univ Sch Math & Comp Dept Computat Sci & Engn Seoul 03722 South Korea Pohang Univ Sci & Technol POSTECH Dept Artificial Intelligence Pohang 37673 South Korea

graphs are used widely to model complex systems, and detecting anomalies in a graph is an important task in the analysis of complex systems. graph anomalies are patterns in a graph that do not conform to normal patterns expected of the attributes and/or structures of the graph. In recent years, graph neural networks (GNNs) have been studied extensively and have successfully performed difficult machine learning tasks in node classification, link prediction, and graph classification thanks to the highly expressive capability via message passing in effectively learning graph representations. To solve the graph anomaly detection problem, GNN-based methods leverage information about the graph attributes (or features) and/or structures to learn to score anomalies appropriately. In this survey, we review the recent advances made in detecting graph anomalies using GNN models. Specifically, we summarize GNN-based methods according to the graph type (i.e., static and dynamic), the anomaly type (i.e., node, edge, subgraph, and whole graph), and the network architecture (e.g., graph autoencoder, graph convolutional network). To the best of our knowledge, this survey is the first comprehensive review of graph anomaly detection methods based on GNNs.

关键词： anomaly detection Feature extraction Image edge detection Message passing graph neural networks Decoding Deep learning Dynamic graph graph anomaly detection graph neural network node anomaly static graph

来源：评论

学校读者我要写书评

暂无评论

Tackling under-reaching issue in Beta-Wavelet filters with mixup augmentation for graph anomaly detection

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 275卷

作者： Do, Thu Uyen Ta, Viet Cuong VNU Univ Engn & Technol Inst Artificial Intelligence 144 Xuan Thuy St Hanoi 100000 Vietnam VNU Univ Engn & Technol Human Machine Interact Lab 144 Xuan Thuy St Hanoi 100000 Vietnam

While deep learning on graphs has gradually become one of the mainstream for mining real-world graph data, detecting anomaly nodes still remains a challenging issue. The rooting cause is the natural over-smoothing and over-squashing of graph deep learning which becomes more severe in graph anomaly detection tasks. Beta-Wavelet filters are introduced to combat this issue, however, their performance is still limited by both the under-reaching and sparse training data issue. In this work, we first analyze the under-reaching issue of Beta-Wavelet graph Neural Networks under the context of anomaly node classification in a semi-supervised learning paradigm. This problem arises from the limited propagation of supervision signals from labeled nodes, particularly to distant nodes, which restricts the model's ability to capture relevant features across the graph. Based on these insights, we propose Beta-Wavelet Mixup, a simple and flexible data augmentation approach tailored for anomaly detection. Our method effectively utilizes latent domain information to identify potential anomalies, generate synthetic nodes, and establish connections on them. The introduced mixup operator is not only to solve the sparseness in the training nodes but also allow more signal propagation by adding mixing edges. To evaluate our approach, we experiment on five popular graph anomaly detection datasets where our method outperforms the other baselines significantly.

关键词： graph anomaly detection graph neural networks Data augmentation Mixup operator

来源：评论

学校读者我要写书评

暂无评论

Multi-view graph anomaly detection via subgraph anomaly augmentation

引用

NEUROCOMPUTING 2025年 637卷

作者： Lin, Fu Zhang, Yue Luo, Xuexiong Li, Mingkang Wang, Zitong Song, Enfeng Wuhan Univ Sch Cyber Sci & Engn Key Lab Aerosp Informat Secur & Trusted Comp Minist Educ Wuhan Hubei Peoples R China Wuhan Univ Sch Comp Sci Wuhan Hubei Peoples R China Macquarie Univ Sch Comp Sydney NSW Australia Wuhan Univ Renmin Hosp Wuhan Hubei Peoples R China

graph anomaly detection (GAD) aims to identify abnormal patterns whose structure and attributes deviate from those of the majority of nodes, and it has been widely applied in various real-world scenarios, such as social network analysis and financial fraud detection. However, most existing GAD methods primarily focus on detecting anomalies in a single view of graph structures, while in real-world scenarios, attributed graphs often possess multi-view graph structures. For instance, in social networks, users may perform various types of interactive actions such as liking, bookmarking, and commenting, thereby forming multi-view attributed graphs with a variety of graph structures. Most existing methods struggle to handle multi-view attributed graphs and fail to capture the underlying interactions between various views, leading to suboptimal performance. Therefore, how to take various types of views into account for anomaly detection remains a challenging task. Moreover, the sparsity of anomalous nodes also limits the performance of existing methods. In this paper, we propose a novel Multi-view graph anomaly detection via subgraph anomaly augmentation, namely MulGAD. First, we fuse subgraph sampling from different views to capture the semantic interactions among them. Second, we utilize subgraph anomaly data augmentation to enhance the model's perception of anomalies. Finally, we train our model by contrastive learning. Thus, MulGAD has the anomaly-aware ability to recognize rare anomaly patterns. Experiments show that MulGAD has excellent anomaly detection performance on four public datasets and maintains stable anomaly-aware ability across different ratios of anomalies.

关键词： Multi-view graphs graph anomaly detection graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Identifying local useful information for attribute graph anomaly detection

引用

NEUROCOMPUTING 2025年 617卷

作者： Xi, Penghui Cheng, Debo Lu, Guangquan Deng, Zhenyun Zhang, Guixian Zhang, Shichao Guangxi Normal Univ Guangxi Key Lab Multisource Informat Min & Secur Guilin Peoples R China Univ South Australia UniSA STEM Adelaide Australia Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu Peoples R China China Univ Min & Technol Sch Comp Sci & Technol Xuzhou Jiangsu Peoples R China

graph anomaly detection primarily relies on shallow learning methods based on feature engineering and deep learning strategies centred on autoencoder-based reconstruction. However, these methods frequently fail to harness the local attributes and structural information within graph data, making it challenging to capture the underlying distribution in scenarios with class-imbalanced graph anomalies, which can result in overfitting. To deal with the above issue, this paper proposes anew anomaly detection method called LIAD (Identifying Local Useful Information for Attribute graph anomaly detection), which learns the data's underlying distribution and captures richer local information. First, LIAD employs data augmentation techniques to create masked graphs and pairs of positive and negative subgraphs. Then, LIAD leverages contrastive learning to derive rich embedding representations from diverse local structural information. Additionally, LIAD utilizes a variational autoencoder (VAE) to generate new graph data, capturing the neighbourhood distribution within the masked graph. During the training process, LIAD aligns the generated graph data with the original to deepen its comprehension of local information. Finally, anomaly scoring is achieved by comparing the discrimination and reconstruction scores of the contrastive pairs, enabling effective anomaly detection. Extensive experiments on five real-world datasets demonstrate the effectiveness of LIAD compared to state-of-the-art methods. Comprehensive ablation studies and parametric analyses further affirm the robustness and efficacy of our model.

关键词： graph neural networks Contrastive learning graph anomaly detection Variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

graph anomaly detection via Multi-Scale Reconstruction of graph Encoder-Decoder Networks

Graph Anomaly Detection via Multi-Scale Reconstruction of Gr...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Yu, Jiaqi Yang, Hong Zhang, Peng Cyberspace Institute of Advanced Technology Guangzhou University Guangzhou China

ISBN: (纸本)9798350368741

Existing unsupervised graph anomaly detection (GAD) methods can be categorized into reconstruction based methods and contrastive learning based methods. The principle of reconstruction methods is to capture anomalous nodes based on data reconstruction errors. However, existing reconstruction methods are limited to a single scale reconstruction of graph structures, typically predicting edges solely based on direct connections, without considering the rich contextual information within node neighborhoods. Moreover, reconstructing original low-density inputs usually introduce noise, where the reconstruction model may overfit the anomalous data. To this end, we propose a new reconstruction based graph anomaly detection method (GADMR for short). GADMR introduces a multi-scale reconstruction, which contains both structure and feature levels. From structure level, we use a node-subgraph reconstruction method to capture the relationship between a node and their neighboring subgraphs at multiple scales. From feature level, we employ a multi-layer representation reconstruction method to facilitate the evaluation of discrepancies in high-level feature representations. Extensive experiments on six benchmark datasets show that GADMR outperforms popular anomaly detection methods. © 2025 IEEE.

关键词： graph anomaly detection graph autoencoders graph neural networks unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：