A cheap feature selection approach for the K -means algorithm
The increase in the number of features that need to be analyzed in a wide variety of areas, such as genome sequencing, computer vision or sensor networks, represents a challenge for the K-means algorithm. In this regard, different dimensionality reduction approaches for the K-means algorithm have be...
| Autores: | , , |
|---|---|
| Tipo de recurso: | artículo |
| Estado: | Versión aceptada para publicación |
| Fecha de publicación: | 2021 |
| País: | España |
| Institución: | Basque Center for Applied Mathematics (BCAM) |
| Repositorio: | BIRD. BCAM's Institutional Repository Data |
| OAI Identifier: | oai:bird.bcamath.org:20.500.11824/1298 |
| Acceso en línea: | http://hdl.handle.net/20.500.11824/1298 |
| Access Level: | acceso abierto |
| Palabra clave: | Dimensionality reduction K-means clustering Feature selection, parallelization |
| Sumario: | The increase in the number of features that need to be analyzed in a wide variety of areas, such as genome sequencing, computer vision or sensor networks, represents a challenge for the K-means algorithm. In this regard, different dimensionality reduction approaches for the K-means algorithm have been designed recently, leading to algorithms that have proved to generate competitive clusterings. Unfortunately, most of these techniques tend to have fairly high computational costs and/or might not be easy to parallelize. In this work, we propose a fully-parellelizable feature selection technique intended for the K-means algorithm. The proposal is based on a novel feature relevance measure that is closely related to the K-means error of a given clustering. Given a disjoint partition of the features, the technique consists of obtaining a clustering for each subset of features and selecting the m features with the highest relevance measure. The computational cost of this approach is just O(m · max{n · K, log m}) per subset of features. We additionally provide a theoretical analysis on the quality of the obtained solution via our proposal, and empirically analyze its performance with respect to well-known feature selection and feature extraction techniques. Such an analysis shows that our proposal consistently obtains results with lower K-means error than all the considered feature selection techniques: Laplacian scores, maximum variance, multi-cluster feature selection and random selection, while also requiring similar or lower computational times than these approaches. Moreover, when compared to feature extraction techniques, such as Random Projections, the proposed approach also shows a noticeable improvement in both error and computational time. |
|---|