Spectral Clustering Method Research Articles

RESKM: A General Framework to Accelerate Large-Scale Spectral Clustering

Spectral Clustering is an effective preprocessing method in communities for its excellent performance, but its scalability still is a challenge. Many efforts have been made to face this problem, and several solutions are proposed, including Nyström Approximation, Sparse Representation Approximation, etc. However, according to our survey, there is still a large room for improvement. This work thoroughly investigates the factors relevant to large-scale Spectral Clustering and proposes a general framework to accelerate Spectral Clustering by utilizing the Robust and Efficient Spectral k-Means (RESKM). The contributions of RESKM are three folds: (1) a unified framework is proposed for large-scale Spectral Clustering; (2) it consists of four phases, each phase is theoretically analyzed, and the corresponding acceleration is suggested; (3) the majority of the existing large-scale Spectral Clustering methods can be integrated into RESKM and therefore be accelerated. Experiments on datasets with different scalability demonstrate that the robustness and efficiency of RESKM.

Non-negative low-rank representation based on dictionary learning for single-cell RNA-sequencing data analysis

In the analysis of single-cell RNA-sequencing (scRNA-seq) data, how to effectively and accurately identify cell clusters from a large number of cell mixtures is still a challenge. Low-rank representation (LRR) method has achieved excellent results in subspace clustering. But in previous studies, most LRR-based methods usually choose the original data matrix as the dictionary. In addition, the methods based on LRR usually use spectral clustering algorithm to complete cell clustering. Therefore, there is a matching problem between the spectral clustering method and the affinity matrix, which is difficult to ensure the optimal effect of clustering. Considering the above two points, we propose the DLNLRR method to better identify the cell type. First, DLNLRR can update the dictionary during the optimization process instead of using the predefined fixed dictionary, so it can realize dictionary learning and LRR learning at the same time. Second, DLNLRR can realize subspace clustering without relying on spectral clustering algorithm, that is, we can perform clustering directly based on the low-rank matrix. Finally, we carry out a large number of experiments on real single-cell datasets and experimental results show that DLNLRR is superior to other scRNA-seq data analysis algorithms in cell type identification.

One step multi-view spectral clustering via joint adaptive graph learning and matrix factorization

Multi-view clustering based on graph learning has attracted extensive attention due to its simplicity and efficiency in recent years. However, there are still some issues in most of the existing graph-based multi-view clustering methods. First, most of those methods require post-processing such as K-means or spectral rotation to get the final discrete clustering result. Second, graph-based clustering methods perform clustering on a fixed input similarity graph, which could induce bad clustering results if the initial graph is with low quality. Third, these methods have high computation cost, which hinders them for dealing with large-scale data. In order to solve these problems, we propose a multi-view spectral clustering method via joint Adaptive Graph Learning and Matrix Factorization (AGLMF). In this method, to reduce computational cost, we adopt the anchor-based strategy to construct the input similarity graphs. Then, we use the l1-norm to learn a high quality similarity graph adaptively from original similarity graphs which can make the final graph more robust than original ones. In addition, AGLMF uses symmetric non-negative matrix factorization to learn the final clustering indicators which can show the final consistent clustering result directly. Finally, experimental results on multiple multi-view datasets validate the effectiveness of the proposed algorithm when compared with previous multi-view spectral clustering algorithms. The demo code of this work is publicly available at https://github.com/theywq/AGLMF.git.

Graph-based medicine embedding learning via multiple attentions

Clinical knowledge reasoning provides a new perspective for intelligent diagnosis and therapy. This study constructs a multi-relational medicine-attribute network, which refers to three different types of relationships: inter-medicine, inter-attribute, and medicine-attribute. Then, a multi-relation-based graph attention network (GAT) model combined with the spectral clustering (SC) algorithm, termed MGAT-SC, is presented to train the medicine embeddings and explore the regularity of medicine combinations. Based on real-world clinical data, the GAT model realizes the information aggregation of neighbor nodes and generates the embeddings of medicines and their attributes via a multi-head attention mechanism. Then, the SC method is utilized to divide the medicines and their embeddings. We design and conduct a series of experiments to verify the model’s performance. The experimental results show that the MGAT-SC outperforms the representative baselines and their variants in terms of five evaluation metrics and achieves around 6.0% improvement in accuracy compared to the SC algorithm.

Meta Path-Aware Recommendation Method Based on Non-Negative Matrix Factorization in LBSN

Location-based social networks (LBSN) is a new type of heterogeneous information network (HIN). The check-in data usually has the characteristics of a large amount of data and high sparsity. It is a problem worth studying how to effectively discover its complex community structure and accurately recommend it to users. Most HIN-based recommendation methods rely on path-based similarity, which cannot fully mine latent structure features of LBSN users and items. This paper proposes a meta-path-aware common clustering recommendation method MPNMF (meta-path-aware non-negative matrix factorization), based on non-negative matrix tri-factorization. By establishing the objective function based on non-negative matrix tri-factorization and second-order meta-path method, LBSN users and points of interest are integrated with their multi-dimensional heterogeneous relationships. The interrelated user clusters and interest point clusters can be obtained, effectively alleviating the influence of data sparsity. To solve the initial value problem of the model, this method uses the spectral cluster method, which provides a good initial value for the construction of the prediction model. It improves the operational efficiency of the model and the precision of model recommendations. Experiments on the real LBSN datasets show that the proposed method has a high recommendation precision and recall.

Estimating mixed-memberships using the symmetric laplacian inverse matrix

Mixed membership community detection is a challenging problem. In this paper, to detect mixed memberships, we propose a new method Mixed-SLIM which is a spectral clustering method on the symmetrized Laplacian inverse matrix under the degree-corrected mixed membership model. We provide theoretical bounds for the estimation error on the proposed algorithm and its regularized version under mild conditions. Meanwhile, we provide some extensions of the proposed method to deal with large networks in practice. These Mixed-SLIM methods outperform state-of-art methods in simulations and substantial empirical datasets for both community detection and mixed membership community detection problems.

Research on detection mechanism of vessel abnormal behavior based on immune genetic spectral clustering algorithm

Maritime transport accounts for over 90% of global trade, and maritime safety has been confirmed as a vital issue of maritime transport. Accordingly, vessel traffic service system (VTS) is capable of assisting the maritime department to complete real-time supervision of a certain water area and increasing the efficiency of water supervision. However, the VTS system has low effectiveness in vessel anomaly detection and supervision, thus resulting in regulatory blind spot in the VTS system. In this study, a vessel trajectory anomaly detection mechanism is developed using the immune genetic spectral clustering method. Moreover, the contour coefficient of scatter clustering is accurately analyzed, and the clustering center is optimized using the adopted method. On that basis, different abnormal features can be detected, and abnormal detection accuracy can be increased. In this study, the vessel trajectory anomaly detection model is built in accordance with the set sliding window and abnormal threshold parameters of vessel trajectory characteristics. The AIS data of Lianyungang to Qingdao port from March 2021 are selected for experimental analysis. The results suggest that the proposed method outperforms the conventional method in the detection accuracy and the false alarm rate, it facilitates the intelligent and automatic management of vessels by the VTS system.

A Time-Varying Network for Cryptocurrencies

Cryptocurrencies return cross-predictability and technological similarity yield information on risk propagation and market segmentation. To investigate these effects, we build a time-varying network for cryptocurrencies, based on the evolution of return cross-predictability and technological similarities. We develop a dynamic covariate-assisted spectral clustering method to consistently estimate the latent community structure of cryptocurrencies network that accounts for both sets of information. We demonstrate that investors can achieve better risk diversification by investing in cryptocurrencies from different communities. A cross-sectional portfolio that implements an inter-crypto momentum trading strategy earns a 1.08% daily return. By dissecting the portfolio returns on behavioral factors, we confirm that our results are not driven by behavioral mechanisms.

Sample-level weights learning for multi-view clustering on spectral rotation

Multi-view clustering usually yields better results than single-view clustering since it utilizes more information from multi-view data. However, in the original multi-view data, some samples may be corrupted in partial views. Under this situation, the locations of the corrupted data are often unknown. But there is limited literature regarding this problem. Moreover, most existing multi-view spectral clustering methods need a post-processed algorithm k-means after obtaining the partition matrix, which leads to deviations in the clustering results. To resolve these problems, we propose a multi-view spectral clustering method named sample-level weights learning for Multi-view Clustering on Spectral Rotation (SR-MC) in this paper. By learning the weights in the sample level, SR-MC can make full use of the helpful complementary information among different views while reducing the effects of low-quality data for each sample. Therefore, it can deal with various multi-view clustering scenarios such as data are complete or corrupted in partial views. To reduce the deviations of the clustering results, a joint framework is designed for combining the learning of the consensus Laplacian matrix, the real-valued partition matrix and the binary indicator matrix together. The objective function of SR-MC can be efficiently optimized by an alternative optimization algorithm. Compared with other ten baselines, experiments on seven datasets show the superiority of our method.

Submarine Landslide Susceptibility and Spatial Distribution Using Different Unsupervised Machine Learning Models

A submarine landslide is a well-known geohazard that can cause significant damage to offshore engineering facilities. Most standard predicting and mapping methods require expert knowledge, supervision, and fieldwork. In this research, the main objective was to analyze the potential of unsupervised machine learning methods and compare the performance of three different unsupervised machine learning models (k-means, spectral clustering, and hierarchical clustering) in modeling the susceptibility of the submarine landslide. Nine groups of geological factors were selected as the input parameters, which were obtained through field surveys. To estimate submarine landslide susceptibility, all input factors were separated into three or four groups based on data features and environmental variables. Finally, the goodness-of-fit and accuracy of models were validated with both internal metrics (Calinski–Harabasz index, silhouette index, and Davies–Bouldin index) and external metrics (existing landslide distribution, hydrodynamic distribution, and liquefication distribution). The findings of k-means, spectral clustering, and hierarchical clustering performed commendably and accurately in forecasting the submarine landslide susceptibility. Spectral clustering has the greatest congruence with environmental geology parameters. Therefore, the unsupervised machine learning model can be used in submarine-landslide-predicting studies, and the spectral clustering method performed best. Furthermore, machine learning can improve submarine landslide mapping in the future with the development of models and the extension of geological data related to submarine landslides.

Data-Clustering Analysis of Scanning Ultrafast Acoustic Experiments: Revealing Acoustic and Structural Properties of a Motoneuron

Ultrafast acoustic imaging experiments are a powerful tool to investigate, at the nanometer scale, cell mechanical properties such as stiffness, viscosity, and adhesion, properties that play some roles in the life and death of cells. However, due to cell complex structures, the ultrafast acoustic signal analysis is quite intricate and depends on multiple parameters. Complex data analysis with poorly known parameters can be handled by a data clustering method as already shown in particle physics and biology. In this work, ultrafast acoustic data analysis is tackled by a spectral clustering method followed by a hierarchical agglomerating method. Coupled to conventional microscopy performed on the very same cell, the clustered data can be assigned to inner-cell features such as the nucleus, the cytoplasm, and the cytoskeleton. The signal dependency on the cell thickness and stiffness is highlighted. Moreover, thanks to the improvement of the signal-to-noise ratio, the nature of the adhesion is also assessed through observation and characterization of a polymerlike layer as thin as a few nanometers.

(Retracted) Deep graph convolutional network-based high-performance detection method for spectral domain gesture image stream

The use of vision-based high-performance detection technology has become an innovative technical methodology. Gestures can express more actions and even emotions, which is more in line with the design idea of large-scale integrated human–computer interaction software, and then assists the development of emotion recognition and other fields. The emerging deep graph convolutional network can capture the interdependence between instances, and then infer the complete information of the image based on specific features. The two-dimensional discrete wavelet and multi-resolution analysis are used to replace the traditional Fourier transform to realize the convolution operation, which improves the accuracy of the generated graph data. This work studies the spectral clustering method of Graph Wavelet Neural Network and adds the local correlation preserving support vector machine as a classifier. This classifier has a simplified structure compared with the cascade classifier and can achieve faster and stable classification results. On the test set, the average accuracy of the algorithm is 93.40%, the recall rate is 96.27%, and the average detection time per frame is 359 ms.

Fast and accurate spectral clustering via augmented Lagrangian

Spectral clustering is one of the most popular general-purpose clustering methods due to its effectiveness and applications in various contexts. Spectral clustering, in its original form, is a two-step method. First, a new representation in which data points could be easily clustered is found. Then, a simple clustering algorithm like k-means is applied. In this paper, we propose a novel and highly accurate method for spectral clustering, called spectral clustering via augmented Lagrangian (SCAL). Specifically, we formalize the spectral clustering problem as a constrained optimization problem, which is challenging to solve due to the orthogonality constraint. This constraint ensures the orthogonality of the dimensions of the new representation where samples of a specific cluster are as close as possible to each other. We then use the augmented Lagrangian method to dispose of the orthogonality constraint and form a new unconstrained cost function. Finally, the new unconstrained problem is solved using the Adam optimization technique. The proposed method is compared to the state-of-the-art methods using synthetic and real-world datasets. Results show that SCAL significantly outperforms other methods in terms of accuracy.

A novel biomarker selection method combining graph neural network and gene relationships applied to microarray data

BackgroundThe discovery of critical biomarkers is significant for clinical diagnosis, drug research and development. Researchers usually obtain biomarkers from microarray data, which comes from the dimensional curse. Feature selection in machine learning is usually used to solve this problem. However, most methods do not fully consider feature dependence, especially the real pathway relationship of genes.ResultsExperimental results show that the proposed method is superior to classical algorithms and advanced methods in feature number and accuracy, and the selected features have more significance.MethodThis paper proposes a feature selection method based on a graph neural network. The proposed method uses the actual dependencies between features and the Pearson correlation coefficient to construct graph-structured data. The information dissemination and aggregation operations based on graph neural network are applied to fuse node information on graph structured data. The redundant features are clustered by the spectral clustering method. Then, the feature ranking aggregation model using eight feature evaluation methods acts on each clustering sub-cluster for different feature selection.ConclusionThe proposed method can effectively remove redundant features. The algorithm’s output has high stability and classification accuracy, which can potentially select potential biomarkers.

A fast spectral clustering technique using MST based proximity graph for diversified datasets

Spectral clustering is a popular unsupervised learning technique used for exploratory analysis of complex datasets. In spectral clustering, the efficient construction of a sparse similarity graph is one of the primary concerns because it influences both the clustering performance as well as the computational time. The sparser the similarity graph, the faster the computation of the eigenvectors, thus improving the overall clustering time. In this paper, we propose a parameter-free method to construct a sparse proximity graph based on the intrinsic structural information of the data points. The proposed method first divides the data into several partitions and then determines the pairs of neighboring partitions using the representative points of each partition. We propose a method called inter-partition MST (IPM) to capture the local proximity information of a neighboring pair. The size of the proposed graph is O(N), where N is the number of data points. For clustering, we apply multi-way spectral clustering on the proposed sparse similarity graph. Experimental analyses demonstrate that in terms of cluster quality, computational time and sparsity of the graph, the proposed algorithm outperforms the other spectral clustering methods.

Associations of built environments with spatiotemporal patterns of shared scooter use: A comparison with shared bike use

This article presents a comparative study aimed at clarifying the similarities and differences between scooter sharing service (SSS) and bike sharing service (BSS) uses in terms of the link between built environments and spatiotemporal patterns. The data comprise study observations from the rental records of SSS and BSS in Taipei, Taiwan. These data were analyzed using spectral clustering method and logit models. The comparison results between SSS and BSS suggest that motorized vehicle usage and high usage cost result in SSS uses revealing long travel distances and different associations of built environments with spatiotemporal patterns from BSS uses. The distance-to-transit variables are related to the spatiotemporal patterns of BSS uses but are unrelated to those of SSS. The difference indicates that existing knowledge on BSS is partially inapplicable to SSS and provides valuable information for transport planners in developing cooperation plans among different transport systems in a city.

Probabilistic Optimal Power Flow-Based Spectral Clustering Method Considering Variable Renewable Energy Sources

Power system clustering is an effective method for realizing voltage control and preventing failure propagation. Various approaches are used for power system clustering. Graph-theory-based spectral clustering methods are widely used because they follow a simple approach with a short calculation time. However, spectral clustering methods can only be applied in system environments for which the power generation amount and load are known. Moreover, it is often impossible to sufficiently reflect the influence of volatile power sources (e.g., renewable energy sources) in the clustering. To this end, this study proposes a probabilistic spectral clustering algorithm applicable to a power system, including a photovoltaic (PV) model (for volatile energy sources) and a classification method (for neutral buses). The algorithm applies a clustering method that reflects the random outputs of PV sources, and the neutral buses can be reclassified via clustering to obtain optimal clustering results. The algorithm is verified through an IEEE 118-bus test system, including PV sources.

SCAR

Spectral clustering is one of the most advantageous clustering approaches. However, standard Spectral Clustering is sensitive to noisy input data and has a high runtime complexity. Tackling one of these problems often exacerbates the other. As real-world datasets are often large and compromised by noise, we need to improve both robustness and runtime at once. Thus, we propose Spectral Clustering - Accelerated and Robust (SCAR), an accelerated, robustified spectral clustering method. In an iterative approach, we achieve robustness by separating the data into two latent components: cleansed and noisy data. We accelerate the eigendecomposition - the most time-consuming step - based on the Nyström method. We compare SCAR to related recent state-of-the-art algorithms in extensive experiments. SCAR surpasses its competitors in terms of speed and clustering quality on highly noisy data.

Anomaly Detection of Dam Monitoring Data based on Improved Spectral Clustering

<p>In response to the abnormal data mining in dam safety monitoring, and based on the traditional spectral clustering, this paper presents an anomaly detection method based on improved spectral clustering. This method applies a distance and density adaptive similarity measure. The natural eigenvalue is introduced to adaptively select the neighbors of data points, and the similarity is redefined to be combined with the natural k-nearest neighbor. Furthermore, the shared neighbor is introduced to adjust the similarity between the monitoring data samples according to the regional density. Moreover, considering the distribution of dam monitoring data, the initialization of clustering centers is optimized according to both the density and distance feature. This method can prevent the algorithm from local optimum, better adapt to the density of non-convex dataset, reduce the number of iterations, and enhance the efficiencies of clustering and anomaly detection. Taking the dam slab monitoring data as the research object, experimental datasets are formed. Experiments on these datasets further verify that the method of this paper can effectively adapt to discrete distribution datasets and is superior to the classical spectral clustering method in both clustering and anomaly detection.</p> <p> </p>

Structured graph optimization for joint spectral embedding and clustering

Spectral Clustering (SC) is an important method in areas such as data mining, image processing, computer science and so on. It attracts more and more attention owing to its effectiveness in unsupervised learning. However, SC has poor performance in the high-dimensional data. Traditional SC methods conduct the spectral embedding of the affinity matrix among data at the first beginning, and then obtain clustering results by the K-means clustering. The also have drawbacks int two processing steps: the clustering results are sensitive to the affinity matrix which may be inaccurate and the post-processing K-means may also be limited by its initialization problem. In the paper, a new approach which joints spectral embedding and clustering with structured graph optimization (called JSEGO) is proposed. In the new model, the low-dimensional representation of data can first be obtained by the spectral embedding method, which can handle with the high-dimensional data better. Then, the optimization similarity matrix would be obtained with such the embedded data. Furthermore, the learning structure graph gives feedback to the similarity matrix to generate better spectral embedded data. As a result, better similarity matrix and clustering result can be obtained by the iterations simultaneously, which are often conducted in two separate steps in the spectral clustering. As a result, the drawbacks introduced by the two processing introduces can be solved. At last, we use an alternative optimization method in the new model and conduct the theoretical analysis by comparing this proposed method with K-means clustering. Experiments based on synthetic data and actual benchmark data prove the advantage of this new approach.