检索结果-内蒙古大学图书馆

Adversarial nonnegative matrix factorization for temporal link prediction

PHYSICS LETTERS A 2024年 527卷

作者： Zhang, Ting Lv, Laishui Bardou, Dalal Nanjing Normal Univ Sch Comp & Elect Informat Nanjing 210023 Peoples R China China Jiliang Univ Coll Informat Engn Hangzhou 310018 Peoples R China Abbes Laghrour Univ Khenchela Dept Comp Sci Khenchela Algeria

Temporal link prediction has been extensively studied and widely applied in various applications, aiming to predict future network links based on the historical networks. However, most existing methods ignore the behavior of previous network updating information in temporal networks. To address these issues, we propose a novel link prediction model based on adversarial nonnegative matrix factorization, which fuses graph representation and adversarial learning to perform temporal link prediction. Specifically, we add a bounded adversary matrix to the input matrix to provide the robustness against real perturbations. Then, our model fully exploits the impact of snapshots by using communicability. Simultaneously, we utilize the cosine similarity to extract the node similarity and map it to low-dimensional latent representation to preserve the local structure. Additionally, we provide effective updating rules to learn the parameters of this model. Extensive experiments results on six real-world networks demonstrate that the proposed method outperforms several classical and the state-of-art matrix-based methods.

关键词： Temporal link prediction Network attacks Adversarial training nonnegative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Robust sparse graph regularized nonnegative matrix factorization for automatic depression diagnosis

引用

BIOMEDICAL SIGNAL PROCESSING AND CONTROL 2024年 93卷

作者： Zhang, Lu Zhong, Jitao Wang, Quanhong Zhu, Jinzhou Liu, Hele Peng, Hong Hu, Bin Lanzhou Univ Sch Informat Sci & Engn Gansu Prov Key Lab Wearable Comp Lanzhou 730000 Peoples R China Lanzhou Univ Lab Special Funct Mat & Struct Design Minist Educ Lanzhou 730000 Peoples R China Beijing Inst Technol Inst Engn Med Brain Hlth Engn Lab Beijing 100081 Peoples R China Lanzhou Univ Res Ctr Open Source Software & Real Time Syst Minist Educ Lanzhou 730000 Peoples R China

Multichannel electroencephalogram (EEG) signals, which directly reflects the brain's inner workings state, is an powerful tool to diagnosis depression. For EEG -based depression diagnosis, appropriate features are important to get a good classification result. Considering the multichannel nature of the EEG signals, the extracted features are generally high -dimensional and contain many redundant features, which impairs the performance of the classifier. Therefore, it is necessary to perform dimensionality reduction. However, existing dimensionality reduction methods are not well suited for EEG data analysis. For this reason, a novel dimensionality reduction algorithm termed correntropy based sparse graph regularized nonnegative matrix factorization (RSGNMF) is proposed. Our RSGNMF solution finds the discriminative low -dimensional representations via joint optimization for better classification. Specifically, RSGNMF adopts correntropy replace the squared Euclidean distance (SED) into nonnegative matrix factorization (NMF) as similarity measure to increase the robustness for noise and outliers, and simultaneously integrating graph regularization and sparse constraints. In order to solve the optimization problem of RSGNMF, the half -quadratic technique was used and subsequently the multiplicative update rule was obtained. Furthermore, convergence and computational complexity of RSGNMF is analyzed. Experimental results reveal the effectiveness of RSGNMF in EEG depression diagnosis in comparison with other state-of-the-art NMF methods. It also shows the practical application value of our method in detecting depression.

关键词： Depression diagnosis Dimensionality reduction EEG nonnegative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

HYPERSHARPENING BASED ON EXTENDED COUPLED nonnegative matrix factorization ADDRESSING SPECTRAL VARIABILITY

HYPERSHARPENING BASED ON EXTENDED COUPLED NONNEGATIVE MATRIX...

引用

IEEE Mediterranean and Middle-East Geoscience and Remote Sensing Symposium (M2GARSS)

作者： Benhalouche, Fatima Zohra Karoui, Moussa Sofiane Brezini, Salah Eddine Deville, Yannick Benkouider, Yasmine Kheira Agence Spatiale Algerienne Ctr Tech Spatiale Arzew Algeria Univ Toulouse CNRS IRAP CNESUPS OMP Toulouse France Univ Sci & Technol Oran Mohamed Boudiaf LSI Oran Algeria

ISBN: (数字)9781665427951

ISBN: (纸本)9781665427951

Hypersharpening results in creating unobservable hyperspectral remote sensing data with high spectral and spatial resolutions, by combining a hyperspectral image, characterized by a high spectral resolution, with a high spatial resolution multispectral one. In this paper, a new hypersharpening method, based on the linear spectral unmixing concept, is proposed. This one, based on a multiplicative nonnegative matrix factorization (NMF) technique, extends the Coupled NMF (CNMF) algorithm by addressing the spectral variability phenomenon. The introduced algorithm that uses multiplicative and iterative update rules minimizes a cost function that takes into account the specific structure of involved matrices, in order to deal with the spectral variability phenomenon. The proposed method is applied to realistic synthetic data, and its effectiveness is evaluated with established performance criteria. The obtained results show that the developed extended CNMF algorithm yields sharpened hyperspectral data with fine spectral and spatial fidelities. Also, these results demonstrate that the proposed technique outperforms the tested hypersharpening literature approaches.

关键词： Hyper/multispectral imaging data fusion hypersharpening spectral variability linear spectral unmixing nonnegative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Self-supervised Adaptive Kernel nonnegative matrix factorization 5th

Self-supervised Adaptive Kernel Nonnegative Matrix Factoriza...

引用

5th Chinese Conference on Pattern Recognition and Computer Vision (PRCV)

作者： Deng, Furong Zhao, Yang Pei, Jihong Yang, Xuan Shenzhen Univ ATR Key Lab Shenzhen 518060 Peoples R China Shenzhen Univ Coll Comp Sci & Software Engn Shenzhen 518060 Peoples R China Shenzhen Univ Guangdong Key Lab Intelligent Informat Proc Shenzhen 518060 Peoples R China

ISBN: (纸本)9783031189067;9783031189074

The kernel function to imply nonlinear mapping is crucial for kernel nonnegative matrix factorizations (KNMF), which determines whether the model can properly represent the data. However, the analysis and adaptive learning of parameters in the kernel function are lacking in existing methods. The kernel parameters of most methods are randomly selected, and the purpose and motivation of kernel function construction is weak. To address this problem, a self-supervised adaptive kernel nonnegative matrix factorization (SAKNMF) is proposed to handle image recognition tasks. Kernel methods are used to achieve non-linearization. Firstly, the data is devided into multiple clusters by fuzzy clustering as self-supervised information. Then, according to the self-supervision information, the discriminative constraints that can adaptively learn the kernel parameters are constructed in the objective function. Based on the new objective function, the Gaussian kernel function parameters, basis matrix and coefficient matrix are jointly optimized. The kernel function constructed by the learned parameters enables the nonlinear mapped basis images to cover the mapped samples in the same cluster and distinguish other different clusters. So that the model can finally learn features that reflect the sample difference and have good generalization. Experiments show that our method can learn appropriate kernel width in different datasets, and the recognition accuracy is better than the state-of-the-art methods.

关键词： nonnegative matrix factorization Kernel method Self-supervised learning Adaptive Gaussian kernel

来源：评论

学校读者我要写书评

暂无评论

Memory-Efficient Convex Optimization for Self-Dictionary nonnegative matrix factorization 56

Memory-Efficient Convex Optimization for Self-Dictionary Non...

引用

56th Asilomar Conference on Signals, Systems, and Computers

作者： Tri Nguyen Fu, Xiao Wu, Ruiyuan Oregon State Univ Sch Elect Engn & Comp Sci Corvallis OR 97331 USA Chinese Univ Hong Kong Dept Elect Engn Hong Kong Peoples R China

ISBN: (纸本)9781665459068

The separable nonnegative matrix factorization (NMF) model has been adopted in many applications (e.g., topic modeling and community detection), as it ensures identifiability of the latent factors with polynomial time algorithms under reasonable assumptions. Separable NMF is often formulated as a self-dictionary (SD) sparse regression problem, and algorithms under this formulation can be categorized into two classes, namely, greedy methods and all-at-once convex optimization. The latter has been shown to be more resilient to noise, but has serious scalability issues. Particularly, existing convex optimization algorithms for the SD sparse regression problem cost a memory that grows quadratically with respect to the data size-making it hardly useful in practice. This work puts forth a Frank-Wolfe algorithm to tackle this challenge. The proposed method has a memory cost that grows linearly in the data size-with provable guarantees. To our best knowledge, this is the first linear memory algorithm for this long-existing problem. Synthetic and real data experiments are used to showcase the memory efficiency of the proposed algorithm.

关键词： nonnegative matrix factorization separability identifiability memory-efficient algorithm Frank-Wolfe

来源：评论

学校读者我要写书评

暂无评论

A family of descent spectral three-term conjugate gradient methods based on the quasi-Newton aspects with applications to nonnegative matrix factorization and image restoration

引用

NUMERICAL ALGORITHMS 2025年 1-32页

作者： Khoshsimaye-Bargard, Maryam Ashrafi, Ali Semnan Univ Fac Math Stat & Comp Sci Dept Math POB 35131-19111 Semnan Iran

A family of descent spectral three-term conjugate gradient methods is introduced in which the coefficient of the third term is determined by approaching its search direction to the memoryless DFP (Davidon-Fletcher-Powell) update. In addition, the spectral parameter is computed in such a way as to ensure the sufficient descent condition for the general objective functions. The convergence analysis is discussed under standard assumptions for nonconvex optimization problems. Moreover, the complexity analysis is established under the Armijo line search strategy. The practical merits of the proposed algorithm are computationally demonstrated on a set of CUTEr test functions as well as the nonnegative matrix factorization problem. To strengthen the numerical results from a practical point of view, further experiments are conducted on the well-known image restoration problem as a real-world case study. Finally, a summarized analysis of the outputs is provided, which mainly demonstrates the practical advantages of the suggested algorithm.

关键词： Unconstrained optimization Conjugate gradient method DFP update Global convergence Complexity analysis nonnegative matrix factorization Image restoration

来源：评论

学校读者我要写书评

暂无评论

Joint nonnegative matrix factorization and network embedding for graph co-clustering

引用

NEUROCOMPUTING 2021年 462卷 453-465页

作者： Wang, Yan Ma, Xiaoke Xidian Univ Sch Comp Sci & Technol POB 1632 South TaiBai Rd Xian Shaanxi Peoples R China Xidian Univ Dept Lib Xian Shaanxi Peoples R China Nanjing Univ State Key Lab Novel Software Technol Nanjing Jiangsu Peoples R China

Graph co-clustering aims to simultaneously group heterogeneous vertices in bipartite networks. The current algorithms measure similarity of vertices by either topology or latent feature of networks, which is insufficient to fully characterize the structure of bipartite graphs. To overcome this problem, we propose a novel co-clustering algorithm by jointly integrating network embedding and NMF (called NENMF) based on the fact that graph representation learning implicitly implies matrix factorizations, where multiple views of bipartite networks are integrated for graph co-clustering. Specifically, the equivalence between nonnegative matrix factorization (NMF) graph embedding for co-clustering is proven, which serves as the theoretical foundation for the proposed algorithm. Then, two auxiliary graphs are generated to fully characterize the topology structure of bipartite networks. Finally, NENMF jointly learns low-rank approximation matrices for bipartite networks and network embedding of auxiliary graphs, where network embedding is regularized into objective function of NMF. The main advantage of the proposed algorithm is to boost the accuracy by combining the low-dimensional approximation and graph representation of bipartite networks without increasing time complexity. The experimental results demonstrate that NENMF outperforms state-of-the-art approaches in terms of accuracy. (c) 2021 Elsevier B.V. All rights reserved.

关键词： Graph co-clustering Bipartite networks nonnegative matrix factorization Network embedding

来源：评论

学校读者我要写书评

暂无评论

Vehicle Face Re-identification Based on nonnegative matrix factorization with Time Difference Constraint

引用

KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS 2021年第6期15卷 2098-2114页

作者： Ma, Na Wen, Tingxin Liaoning Tech Univ Sch Business Adm Huludao Liaoning Peoples R China

Light intensity variation is one of the key factors which affect the accuracy of vehicle face re-identification, so in order to improve the robustness of vehicle face features to light intensity variation, a nonnegative matrix factorization model with the constraint of image acquisition time difference is proposed. First, the original features vectors of all pairs of positive samples which are used for training are placed in two original feature matrices respectively, where the same columns of the two matrices represent the same vehicle;Then, the new features obtained after decomposition are divided into stable and variable features proportionally, where the constraints of intra-class similarity and inter-class difference are imposed on the stable feature, and the constraint of image acquisition time difference is imposed on the variable feature;At last, vehicle face matching is achieved through calculating the cosine distance of stable features. Experimental results show that the average False Reject Rate and the average False Accept Rate of the proposed algorithm can be reduced to 0.14 and 0.11 respectively on five different datasets, and even sometimes under the large difference of light intensities, the vehicle face image can be still recognized accurately, which verifies that the extracted features have good robustness to light variation.

关键词： Vehicle face re-identification nonnegative matrix factorization stable feature variable feature cosine distance

来源：评论

学校读者我要写书评

暂无评论

Noise Robust Acoustic Anomaly Detection System with nonnegative matrix factorization Based on Generalized Gaussian Distribution

引用

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS 2021年第3期E104D卷 441-449页

作者： Aiba, Akihito Yoshida, Minoru Kitamura, Daichi Takamichi, Shinnosuke Saruwatari, Hiroshi Ricoh Co Ltd Ebina Kanagawa 2430460 Japan Natl Inst Technol Kagawa Coll Takamatsu Kagawa 7618058 Japan Univ Tokyo Tokyo 1138656 Japan

We studied an acoustic anomaly detection system for equipments, where the outlier detection method based on recorded sounds is used. In a real environment, the SNR of the target sound against background noise is low, and there is the problem that it is necessary to catch slight changes in sound buried in noise. In this paper, we propose a system in which a sound source extraction process is provided at the preliminary stage of the outlier detection process. In the proposed system, non-negative matrix factorization based on generalized Gaussian distribution (GGD-NMF) is used as a sound source extraction process. We evaluated the improvement of the anomaly detection performance in a low-SNR environment. In this experiment, SNR capable of detecting an anomaly was greatly improved by providing GGD-NMF for preprocessing.

关键词： nonnegative matrix factorization generalized Gaussian distribution anomaly detection outlier detection

来源：评论

学校读者我要写书评

暂无评论

Class-driven nonnegative matrix factorization with manifold regularization for data clustering

引用

NEUROCOMPUTING 2024年 592卷

作者： Li, Huirong Zhou, Yani Zhao, Pengjun Wang, Lei Yu, Chengxiang Shangluo Univ Sch Math & Comp Applicat Shangluo 726000 Peoples R China Shangluo Univ Sch Hlth Management Shangluo 726000 Peoples R China Univ Shaanxi Prov Engn Res Ctr Qinling Hlth Welf Big Data Shangluo 726000 Peoples R China

nonnegative matrix factorization (NMF) is an effective technique to extract the underlying low -dimensional structure of data by utilizing its parts -based representation, which has been widely used in feature extraction and machine learning. However, NMF is an unsupervised learning algorithm without utilizing the discriminative prior information. In this paper, we put forward a new class -driven NMF with manifold regularization (MCDNMF) algorithm, which incorporates both the local manifold regularization and the label information of data into the NMF model. Specifically, MCDNMF not only encodes the local geometrical structure of data space by using the manifold regularization, but also takes the available label information by introducing the class -driven constraint. This class -driven constraint forces the new representations of data points to be more similar within the same class while different between other classes. Therefore, the discriminative abilities of clustering are greatly boosted. Experimental results on several datasets validate the effectiveness of proposed MCDNMF in comparison with the other state-of-the-art methods.

关键词： nonnegative matrix factorization Manifold regularization Semi-supervised learning Class-driven constraint

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：