Spectral clustering with adaptive similarity measure in Kernel space

LSEC: Large-scale spectral ensemble clustering

A fundamental problem in machine learning is ensemble clustering, that is, combining multiple base clusterings to obtain improved clustering result. However, most of the existing methods are unsuitable for large-scale ensemble clustering tasks owing to efficiency bottlenecks. In this paper, we propose a large-scale spectral ensemble clustering (LSEC) method to balance efficiency and effectiveness. In LSEC, a large-scale spectral clustering-based efficient ensemble generation framework is designed to generate various base clusterings with low computational complexity. Thereafter, all the base clusterings are combined using a bipartite graph partition-based consensus function to obtain improved consensus clustering results. The LSEC method achieves a lower computational complexity than most existing ensemble clustering methods. Experiments conducted on ten large-scale datasets demonstrate the efficiency and effectiveness of the LSEC method. The MATLAB code of the proposed method and experimental datasets are available at https://github.com/Li-Hongmin/MyPaperWithCode.

Noises Cutting and Natural Neighbors Spectral Clustering Based on Coupling P System

Clustering analysis, a key step for many data mining problems, can be applied to various fields. However, no matter what kind of clustering method, noise points have always been an important factor affecting the clustering effect. In addition, in spectral clustering, the construction of affinity matrix affects the formation of new samples, which in turn affects the final clustering results. Therefore, this study proposes a noise cutting and natural neighbors spectral clustering method based on coupling P system (NCNNSC-CP) to solve the above problems. The whole algorithm process is carried out in the coupled P system. We propose a natural neighbors searching method without parameters, which can quickly determine the natural neighbors and natural characteristic value of data points. Then, based on it, the critical density and reverse density are obtained, and noise identification and cutting are performed. The affinity matrix constructed using core natural neighbors greatly improve the similarity between data points. Experimental results on nine synthetic data sets and six UCI datasets demonstrate that the proposed algorithm is better than other comparison algorithms.

Multiclass spectral feature scaling method for dimensionality reduction

Irregular features disrupt the desired classification. In this paper, we consider aggressively modifying scales of features in the original space according to the label information to form well-separated clusters in low-dimensional space. The proposed method exploits spectral clustering to derive scaling factors that are used to modify the features. Specifically, we reformulate the Laplacian eigenproblem of the spectral clustering as an eigenproblem of a linear matrix pencil whose eigenvector has the scaling factors. Numerical experiments show that the proposed method outperforms well-established supervised dimensionality reduction methods for toy problems with more samples than features and real-world problems with more features than samples.

Detecting Interactive Gene Groups for Single-Cell RNA-Seq Data Based on Co-Expression Network Analysis and Subgraph Learning

High-throughput sequencing technologies have enabled the generation of single-cell RNA-seq (scRNA-seq) data, which explore both genetic heterogeneity and phenotypic variation between cells. Some methods have been proposed to detect the related genes causing cell-to-cell variability for understanding tumor heterogeneity. However, most existing methods detect the related genes separately, without considering gene interactions. In this paper, we proposed a novel learning framework to detect the interactive gene groups for scRNA-seq data based on co-expression network analysis and subgraph learning. We first utilized spectral clustering to identify the subpopulations of cells. For each cell subpopulation, the differentially expressed genes were then selected to construct a gene co-expression network. Finally, the interactive gene groups were detected by learning the dense subgraphs embedded in the gene co-expression networks. We applied the proposed learning framework on a real cancer scRNA-seq dataset to detect interactive gene groups of different cancer subtypes. Systematic gene ontology enrichment analysis was performed to examine the detected genes groups by summarizing the key biological processes and pathways. Our analysis shows that different subtypes exhibit distinct gene co-expression networks and interactive gene groups with different functional enrichment. The interactive genes are expected to yield important references for understanding tumor heterogeneity.