Model-based clustering of high-dimensional data: A review

By Charles Bouveyron, Camille Brunet. Computational Statistics & Data Analysis, 2014

473 citations recorded by the source corpus.

Model-based clustering is a popular tool which is renowned for its probabilistic foundations and its flexibility. However, high-dimensional data are nowadays more and more frequent and, unfortunately, classical model-based clustering techniques show a disappointing behavior in high-dimensional spaces. This is mainly due to the fact that model-based clustering methods are dramatically over-parametrized in this case. However, high-dimensional spaces have specific characteristics which are useful for clustering and recent techniques exploit those characteristics. After having recalled the bases of model-based clustering, dimension reduction approaches, regularization-based techniques, parsimonious modeling, subspace clustering methods and clustering methods based on variable selection are reviewed. Existing softwares for model-based clustering of high-dimensional data will be also reviewed and their practical use will be illustrated on real-world data sets.

Subfields: Artificial Intelligence, Signal Processing

View Paper: https://www.semanticscholar.org/paper/b56b8fe0d89e8955b5568e8e4c77799e3d55857a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Signal Processing

Citations in the corpus

Gradient-based training of Gaussian Mixture Models in High-Dimensional Spaces (2019, methodology): “There has been signiﬁcant work on simplifying GMM models (e.g., Jakovljevi´c (2014)), leading to what is called parsimonious GMM models , which is reviewed in Bouveyron & Brunet-Saumard (2014).”
Classes and continua of hippocampal CA1 inhibitory neurons revealed by single-cell transcriptomics (2017, unknown): ““sparse” methods is essential for probabilistic classification of high dimensional data (Bouveyron and Brunet-Saumard, 2014), and the genes selected represent those most informative for cluster differentiation.”
Model-Based Clustering (2016, background): “As Bouveyron and Brunet-Saumard (2014) point out in their excellent review, carrying out these two elements—clustering and dimension reduction—sequentially does not typically work; they give the particular example of clustering after principal component analysis.”
A Systematic Review on Educational Data Mining (2017, unknown): “…& Clustering [41], [115], [116], [117] Learning style & Clustering [118], [80], [119], [120], [121], [122], [123], [124], [125], [126], [127], [128], [129] Self-Organizing Map (SOM) & Clustering [130], [131], [132] Semantic web in education & Clustering [44], [58] Student modeling &…”
A tutorial on task-parameterized movement learning and retrieval (2015, background): “Many possible constraints can be considered, grouped in families such as parsimonious GMM [11, 61, 7], mixtures of factor analyzers (MFA) [60] or mixtures of probabilistic principal component analyzers (MPPCA) [93].”
Spike sorting for large, dense electrode arrays (2015, background): “While solutions to certain types of high-dimensional clustering problems have been found 17 , no solution exists to the specific problem that occurs in spike sorting, in which different points are defined by a different subset of relevant dimensions, and millions of points must be clustered in…”
Functional data clustering: a survey (2013, unknown): “These techniques are not discussed in this paper, and we refer to [11] for a complete review on the subject.”