检索结果-内蒙古大学图书馆

An unsupervised false data detection method based on graph autoencoder and attention network in power grid

ELECTRICAL ENGINEERING 2025年第1期107卷 869-881页

作者： Yang, Yingjie Cai, Tiantian Liu, Dehong Li, Xueping Wang, Yaokun Lu, Zhigang China Southern Power Grid Digital Grid Res Inst Co Guangzhou 510670 Guangdong Peoples R China Yanshan Univ Key Lab Power Elect Energy Conservat & Motor Dr He Qinhuangdao 066004 Hebei Peoples R China

False Data Injection Attacks (FDIAs) can bypass traditional state estimation detection, which threatens the security of power systems. Data-driven detection is an effective method for detecting FDIAs. However, for supervised detection methods, it is difficult to obtain a large number of anomaly labels in the power system. To address the issue of insufficient anomaly labels, this paper proposes an unsupervised FDIAs detection method based on graph autoencoder and graph attention neural network (GAE-GAT). In the method, the GAE aggregates the characteristics of topology and operation data in power system. To improve node representation, attention mechanism is adopted to aggregate adjacent node weights. This method is tested on the IEEE-14 and 118 bus systems for three scenarios: static topology, dynamic topology, and renewable energy integration. The results demonstrate that compared with previous unsupervised detection methods, the proposed method can greatly improve detection accuracy.

关键词： Unsupervised false data detection Power system security graph autoencoder graph attention neural network

来源：评论

学校读者我要写书评

暂无评论

Spatial-temporal masked graph autoencoder for rotating machinery fault diagnosis with limited data

引用

JOURNAL OF VIBRATION AND CONTROL 2025年

作者： Xiong, Wanquan Han, Yanfeng Wu, Qile Xiao, Ke Song, Bin Chongqing Univ State Key Lab Mech Transmiss Adv Equipments Chongqing 400044 Peoples R China ROKAE Beijing Technol Co Ltd Technol Ctr Beijing Peoples R China

Due to the difficulty and high cost associated with obtaining samples of faults in rotating machinery, current intelligent fault diagnosis methods struggle to extract sufficiently diverse fault features, leading to poor diagnostic performance. Additionally, existing deep learning-based approaches often focus solely on extracting temporal or spatial information from sensor signals, ignoring spatial-temporal correlations. Addressing these issues, a novel spatial-temporal masked graph autoencoder (STMGAE) framework is proposed for fault diagnosis in rotating machinery with limited data. In this proposed methodology, a masked strategy is applied to graph-structured data constructed from multi-sensor signals, enabling the model to enhance feature learning capability by training on incomplete graph-structured data masked accordingly. Furthermore, a spatial-temporal graph attention encoder module is introduced to capture temporal and spatial dependencies. To effectively reconstruct the masked portions of the graph-structured data, a correlation similarity decoder is designed, which achieves the desired outcome by capturing correlation similarity between nodes at different granularities, thus improving the model's performance. Experimental validation of STMGAE's effectiveness in fault diagnosis with limited data is conducted on two publicly available datasets, demonstrating superior performance compared to existing methods.

关键词： fault diagnosis limited data masked strategy graph autoencoder rotating machinery

来源：评论

学校读者我要写书评

暂无评论

Pre-training graph autoencoder incorporating hierarchical topology knowledge

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 265卷

作者： Zhu, Hongyin Li, Yakun Liu, Luyang Tong, Haonan Zhang, Chuang Lin, Qunyang 360 Search Dept Qihoo 360 Beijing Peoples R China Beijing Forestry Univ Sch Informat Sci & Technol Haidian East Rd Beijing 100083 Peoples R China Inspur Elect Informat Ind Co Ltd Architecture Res Dept Beijing Peoples R China Natl Key Lab High end Server Syst Jinan Peoples R China

Existing graph pre-training methods demonstrate their ability to generate vertex representations beneficial for downstream machine-learning tasks. However, the quality of these representations is often influenced by the choice of learning algorithm. While masking strategies are commonly employed, random masks can lead to noisy neighborhoods and incomplete graph topology, hampering learning efficiency and increasing computational costs. When a significant portion of neighbors are randomly masked, the central vertex lacks sufficient contextual information. To address this challenge, we integrate hierarchical topology knowledge to enhance masking strategies, thereby preserving the major topology and minimizing training costs. Our method leverages 3 distinct masking techniques: global-aware, local-aware, and element-aware masking. Global-aware masking encourages the model to capture the graph's overall topology, while local-aware masking focuses on capturing vertex interactions. Element-aware masking enhances the model's robustness against noise and structural variations. By incorporating these 3 strategies, our method mitigates the impact of random noise and structural variations during training, yielding more robust and effective vertex representations. To further optimize the model, we introduce a fine-grained subgraph regularization, which reduces the model's parameter count by penalizing divergence in subgraph embeddings across multiple views. We assess the effectiveness of our approach on 3 datasets, highlighting its performance improvements while achieving a reduction of 25% in model parameters.

关键词： graph pre-training Hierarchical topology knowledge graph autoencoder Subgraph regularization

来源：评论

学校读者我要写书评

暂无评论

Data-Agnostic Model Poisoning Against Federated Learning: A graph autoencoder Approach

引用

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2024年 19卷 3465-3480页

作者： Li, Kai Zheng, Jingjing Yuan, Xin Ni, Wei Akan, Ozgur B. Poor, H. Vincent Univ Cambridge Dept Engn Cambridge CB3 0FA England Real Time & Embedded Comp Syst Res Ctr CISTER P-4249015 Porto Portugal Carnegie Mellon Univ CyLab Secur & Privacy Inst Pittsburgh PA 15213 USA Real Time & Embedded Comp Syst Res Ctr CISTER P-4249015 Porto Portugal Commonwealth Sci & Ind Res Org CSIRO Digital Prod & Serv Flagship Sydney NSW 2122 Australia Univ Cambridge Dept Engn Div Elect Engn Cambridge CB3 0FA England Koc Univ Ctr neXt generat Commun CXC TR-34450 Istanbul Turkiye Princeton Univ Dept Elect & Comp Engn Princeton NJ 08544 USA

This paper proposes a novel, data-agnostic, model poisoning attack on Federated Learning (FL), by designing a new adversarial graph autoencoder (GAE)-based framework. The attack requires no knowledge of FL training data and achieves both effectiveness and undetectability. By listening to the benign local models and the global model, the attacker extracts the graph structural correlations among the benign local models and the training data features substantiating the models. The attacker then adversarially regenerates the graph structural correlations while maximizing the FL training loss, and subsequently generates malicious local models using the adversarial graph structure and the training data features of the benign ones. A new algorithm is designed to iteratively train the malicious local models using GAE and sub-gradient descent. The convergence of FL under attack is rigorously proved, with a considerably large optimality gap. Experiments show that the FL accuracy drops gradually under the proposed attack and existing defense mechanisms fail to detect it. The attack can give rise to an infection across all benign devices, making it a serious threat to FL.

关键词： Federated learning model poisoning attack graph autoencoder feature correlation

来源：评论

学校读者我要写书评

暂无评论

A New graph autoencoder-Based Multi-Level Kernel Subspace Fusion Framework for Single-Cell Type Identification

引用

IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2024年第6期21卷 2292-2303页

作者： Wang, Juan Qiao, Tian-Jing Zheng, Chun-Hou Liu, Jin-Xing Shang, Jun-Liang Qufu Normal Univ Sch Comp Sci Rizhao 276826 Peoples R China

The advent of single-cell RNA sequencing (scRNA-seq) technology offers the opportunity to conduct biological research at the cellular level. Single-cell type identification based on unsupervised clustering is one of the fundamental tasks of scRNA-seq data analysis. Although many single-cell clustering methods have been developed recently, few can fully exploit the deep potential relationships between cells, resulting in suboptimal clustering. In this paper, we propose scGAMF, a graph autoencoder-based multi-level kernel subspace fusion framework for scRNA-seq data analysis. Based on multiple top feature sets, scGAMF unifies deep feature embedding and kernel space analysis into a single framework to learn an accurate clustering affinity matrix. First, we construct multiple top feature sets to avoid the high variability caused by single feature set learning. Second, scGAMF uses a graph autoencoder (GAEs) to extract deep information embedded in the data, and learn embeddings including gene expression patterns and cell-cell relationships. Third, to fully explore the deep potential relationships between cells, we design a multi-level kernel space fusion strategy. This strategy uses a kernel expression model with adaptive similarity preservation to learn a self-expression matrix shared by all embedding spaces of a given feature set, and a consensus affinity matrix across multiple top feature sets. Finally, the consensus affinity matrix is used for spectral clustering, visualization, and identification of gene markers. Extensive validation on real datasets shows that scGAMF achieves higher clustering accuracy than many popular single-cell analysis methods.

关键词： Kernel Feature extraction Data models Clustering methods Adaptation models Accuracy Sequential analysis Consensus learning graph autoencoder kernel self-expression model multi-level kernel space fusion multiple top fea-ture sets single-cell type identification

来源：评论

学校读者我要写书评

暂无评论

graph autoencoder for directed weighted network

引用

SOFT COMPUTING 2022年第3期26卷 1217-1230页

作者： Ma, Yang Li, Yan Liang, Xingxing Cheng, Guangquan Feng, Yanghe Liu, Zhong Natl Univ Def Technol Coll Syst Engn Changsha Peoples R China

Network embedding technology transforms network structure into node vectors, which reduces the complexity of representation and can be effectively applied to tasks such as classification, network reconstruction and link prediction. The main concern of network embedding is to keep the local structural features while effectively capturing the global features of the network. The "shallow" network representation models cannot capture the deep nonlinear features of the network, and the generated network embedding is usually not the optimal solution. In this paper, a new graph autoencoder-based network representation model combines the first- and second-order proximity to evaluate the performance of network embedding. Aiming at the shortcomings of existing network representation methods in weighted and directed networks, on one hand, the concepts of receiving vector and sending vector are introduced with a simplification of decoding part of the neural network which reduces computation complexity;on the other hand, a measurement index based on node degree is proposed to better emphasize the weighted information in the application of network representation. Experiments including directed weighted networks and undirected unweighted networks show that the proposed method achieves better results than the baseline methods for network reconstruction and link prediction tasks and is of higher computation efficiency than previous graph autoencoder algorithms. Besides, the proposed weighted index is able to improve performances of all baseline methods as an external assistance.

关键词： Complex network Network embedding Network reconstruction Link prediction graph autoencoder

来源：评论

学校读者我要写书评

暂无评论

Self-supervised graph autoencoder with redundancy reduction for community detection

引用

NEUROCOMPUTING 2024年 590卷

作者： Wang, Xiaofeng Shen, Guodong Zhang, Zengjie Lai, Shuaiming Zhu, Shuailei Chen, Yuntao Quan, Daying China Jiliang Univ Coll Informat Engn Hangzhou 310018 Peoples R China

Community detection is a significant research topic in network science, which has been revisited with graph neural networks. As a powerful graph representation learning model, graph autoencoder (GAE) is commonly used for unsupervised community detection. However, most GAE-based methods ignore multi -scale features of encoding layers, which inherently provide useful information for community detection. Moreover, these methods fail to simultaneously improve the representation learning process and clustering performance through a unified objective function. To address these issues, we propose a self -supervised graph autoencoder model with redundancy reduction for community detection. Firstly, we introduce a multi -scale module based on GAE to obtain discriminative node representations from different encoding layers. In particular, a redundancy reduction strategy is employed to eliminate redundancy information in the latent embedding space. Then, a node clustering module is used to obtain initial community labels. To fully utilize the multi -scale features to further refine clustering performance, a self -supervised module is designed to utilize current clustering labels to supervise the node representation learning process, thus constructing an end -to -end model for community detection. Finally, we validate the effectiveness of the proposed method on real -world networks. Experimental results demonstrate that our method outperforms several state-of-the-art methods in community detection.

关键词： graph autoencoder Community detection Multi-scale features Self-supervised learning Redundancy reduction

来源：评论

学校读者我要写书评

暂无评论

stAA: adversarial graph autoencoder for spatial clustering task of spatially resolved transcriptomics

引用

BRIEFINGS IN BIOINFORMATICS 2024年第1期25卷 bbad500页

作者： Fang, Zhaoyu Liu, Teng Zheng, Ruiqing Jin, A. Yin, Mingzhu Li, Min Cent South Univ Sch Comp Sci & Engn Changsha 410083 Hunan Peoples R China Chongqing Univ Gorges Hosp 3 Med Pathol Ctr MPC Clin Res Ctr CRCCanc Early Detect & Treatment Ctr Chongqing 404031 Peoples R China

With the development of spatially resolved transcriptomics technologies, it is now possible to explore the gene expression profiles of single cells while preserving their spatial context. Spatial clustering plays a key role in spatial transcriptome data analysis. In the past 2 years, several graph neural network-based methods have emerged, which significantly improved the accuracy of spatial clustering. However, accurately identifying the boundaries of spatial domains remains a challenging task. In this article, we propose stAA, an adversarial variational graph autoencoder, to identify spatial domain. stAA generates cell embedding by leveraging gene expression and spatial information using graph neural networks and enforces the distribution of cell embeddings to a prior distribution through Wasserstein distance. The adversarial training process can make cell embeddings better capture spatial domain information and more robust. Moreover, stAA incorporates global graph information into cell embeddings using labels generated by pre-clustering. Our experimental results show that stAA outperforms the state-of-the-art methods and achieves better clustering results across different profiling platforms and various resolutions. We also conducted numerous biological analyses and found that stAA can identify fine-grained structures in tissues, recognize different functional subtypes within tumors and accurately identify developmental trajectories.

关键词： spatial transcriptomics spatial domain graph neural network adversarial learning graph autoencoder

来源：评论

学校读者我要写书评

暂无评论

SGAE-MDA: Exploring the MiRNA-disease associations in herbal medicines based on semi-supervised graph autoencoder

引用

METHODS 2024年 221卷 73-81页

作者： Xu, Lei Fu, Xiangzheng Zhuo, Linlin Zhou, Zhecheng Liao, Xuefeng Tian, Sha Kang, Ruofei Chen, Yifan Macau Univ Sci & Technol Macau Inst Appl Res Med & Hlth Nehers Biophys Lab Innovat Drug Discovery State Key Lab Qual Res Chinese Med Macau Peoples R China Wenzhou Univ Technol Wenzhou Peoples R China Hunan Univ Coll Informat Sci & Engn Changsha Hunan Peoples R China Hunan Univ Chinese Med Coll Integrated Chinese & Western Med Dept Internal Med Changsha Hunan Peoples R China Xuhui Excellent Hlth Informat Technol Co Ltd Shanghai Peoples R China

Research indicates that miRNAs present in herbal medicines are crucial for identifying disease markers, advancing gene therapy, facilitating drug delivery, and so on. These miRNAs maintain stability in the extracellular environment, making them viable tools for disease diagnosis. They can withstand the digestive processes in the gastrointestinal tract, positioning them as potential carriers for specific oral drug delivery. By engineering plants to generate effective, non-toxic miRNA interference sequences, it's possible to broaden their applicability, including the treatment of diseases such as hepatitis C. Consequently, delving into the miRNA-disease associations (MDAs) within herbal medicines holds immense promise for diagnosing and addressing miRNA-related diseases. In our research, we propose the SGAE-MDA model, which harnesses the strengths of a graph autoencoder (GAE) combined with a semi-supervised approach to uncover potential MDAs in herbal medicines more effectively. Leveraging the GAE framework, the SGAE-MDA model exactly integrates the inherent feature vectors of miRNAs and disease nodes with the regulatory data in the miRNA-disease network. Additionally, the proposed semi-supervised learning approach randomly hides the partial structure of the miRNA-disease network, subsequently reconstructing them within the GAE framework. This technique effectively minimizes network noise interference. Through comparison against other leading deep learning models, the results consistently highlighted the superior performance of the proposed SGAE-MDA model. Our code and dataset can be available at: https://github .com /22n9n23 /SGAE-MDA.

关键词： Herbal medicines MiRNA-disease associations (MDAs) graph autoencoder Semi-supervised approach Network noise

来源：评论

学校读者我要写书评

暂无评论

Bearing Fault Diagnosis via graph autoencoder Networks with Multi-kernel Subdomain Adversarial Domain Adaptation

引用

JOURNAL OF FAILURE ANALYSIS AND PREVENTION 2024年第6期24卷 2831-2846页

作者： Guo, Junfeng Hu, Zeming Wang, Zhiming Zhang, Yushan Lanzhou Univ Technol Sch Mech & Elect Engn Lanzhou 730050 Peoples R China

Unsupervised domain adaptation (UDA) based on transfer learning methods have been widely used in the research of bearing fault diagnosis under variable operating conditions, and some useful results have been achieved. However, conventional UDA methods predominantly prioritize the extraction of class labels and domain labels from the data, neglecting the effect of data architecture information on extracted characteristics. In addition, global domain adaptation methods ignore the relationship between subdomains. Therefore, in this paper, we propose multi-kernel subdomain adversarial domain adaptation for graph autoencoder networks (MSADAGAE) to solve the above problems, which has two key parts. Firstly, multiple graph convolutional blocks are used to obtain graph node features as well as topologies at different scales via residual-connected graph autoencoders (GAEs). Second, a subadaptation module based on multi-layer multi-kernel local maximum mean discrepancy (MLMK-LMMD) is proposed, including a globally aligned domain classifier and subdomain-aligned domain adaptation. Then, the optimization of feature classification boundaries is further enhanced through margin loss regularization. Finally, validation is performed on the public datasets CWRU, JNU, and the results show that the model exhibits good performance even under unbalanced datasets.

关键词： graph autoencoder Margin loss MLMK-LMMD Subdomain adaptation Fault diagnosis

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

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

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：