Clustering Ensemble Meets Low-rank Tensor Approximation (2020-12-16T00:00:00.000000Z)

TL;DR

A novel low-rank tensor approximation based method to solve the problem of clustering ensemble from a global perspective, which is fundamentally different from previous approaches and achieves a breakthrough in clustering performance, compared with 12 state-of-the-art methods.

Abstract

This paper explores the problem of clustering ensemble, which aims to combine multiple base clusterings to produce better performance than that of the individual one. The existing clustering ensemble methods generally construct a co-association matrix, which indicates the pairwise similarity between samples, as the weighted linear combination of the connective matrices from different base clusterings, and the resulting co-association matrix is then adopted as the input of an off-the-shelf clustering algorithm, e.g., spectral clustering. However, the co-association matrix may be dominated by poor base clusterings, resulting in inferior performance. In this paper, we propose a novel low-rank tensor approximation based method to solve the problem from a global perspective. Specifically, by inspecting whether two samples are clustered to an identical cluster under different base clusterings, we derive a coherent-link matrix, which contains limited but highly reliable relationships between samples. We then stack the coherent-link matrix and the co-association matrix to form a three-dimensional tensor, the low-rankness property of which is further explored to propagate the information of the coherent-link matrix to the co-association matrix, producing a refined co-association matrix. We formulate the proposed method as a convex constrained optimization problem and solve it efficiently. Experimental results over 7 benchmark data sets show that the proposed model achieves a breakthrough in clustering performance, compared with 12 state-of-the-art methods. To the best of our knowledge, this is the first work to explore the potential of low-rank tensor on clustering ensemble, which is fundamentally different from previous approaches. Last but not least, our method only contains one parameter, which can be easily tuned.

References34 items

Constrained Clustering With Dissimilarity Propagation-Guided Graph-Laplacian PCA

Joint Optimization for Pairwise Constraint Propagation

Semi-Supervised Non-Negative Matrix Factorization With Dissimilarity and Similarity Regularization

Self-Paced Clustering Ensemble

Semisupervised Adaptive Symmetric Non-Negative Matrix Factorization

Generalized Latent Multi-View Subspace Clustering

Imbalance-aware Pairwise Constraint Propagation

Ensemble clustering based on dense representation

Clustering-Aware Graph Construction: A Joint Learning Perspective

Superpixel Segmentation Based on Square-Wise Asymmetric Partition and Structural Approximation

Enhanced Ensemble Clustering via Fast Propagation of Cluster-Wise Similarities

Convex Constrained Clustering with Graph-Laplacian Pca

Ensemble learning: A survey

Pairwise Constraint Propagation-Induced Symmetric Nonnegative Matrix Factorization

Cluster ensembles: A survey of approaches with recent extensions and applications

Nonnegative matrix factorization with mixed hypergraph regularization for community detection

Semi-Supervised Spectral Clustering With Structured Sparsity Regularization

From Ensemble Clustering to Multi-View Clustering

Spectral Ensemble Clustering via Weighted K-Means: Theoretical and Practical Evidence

Simultaneous Clustering and Ensemble

Robust Spectral Ensemble Clustering

A Robust Convex Formulation for Ensemble Clustering

Locally Weighted Ensemble Clustering

Robust Ensemble Clustering Using Probability Trajectories

Online Learning in Large-Scale Contextual Recommender Systems

Novel Methods for Multilinear Data Completion and De-noising Based on Tensor-SVD

Third-Order Tensors as Operators on Matrices: A Theoretical and Computational Framework with Applications in Imaging