Enhancing K-Means using class labels

Article type: Research Article

Authors: Peralta, Billy^{; *} | Espinace, Pablo | Soto, Alvaro

Affiliations: Pontificia Universidad Católica de Chile, Región Metropolitana, Chile

Correspondence: [*] Corresponding author: Billy Peralta, Pontificia Universidad Católica de Chile, Región Metropolitana, Chile. E-mail: bmperalt@uc.cl.

Abstract: Clustering is a relevant problem in machine learning where the main goal is to locate meaningful partitions of unlabeled data. In the case of labeled data, a related problem is supervised clustering, where the objective is to locate class-uniform clusters. Most current approaches to supervised clustering optimize a score related to cluster purity with respect to class labels. In particular, we present Labeled K-Means (LK-Means), an algorithm for supervised clustering based on a variant of K-Means that incorporates information about class labels. LK-Means replaces the classical cost function of K-Means by a convex combination of the joint cost associated to: (i) A discriminative score based on class labels, and (ii) A generative score based on a traditional metric for unsupervised clustering. We test the performance of LK-Means using standard real datasets and an application for object recognition. Moreover, we also compare its performance against classical K-Means and a popular K-Medoids-based supervised clustering method. Our experiments show that, in most cases, LK-Means outperforms the alternative techniques by a considerable margin. Furthermore, LK-Means presents execution times considerably lower than the alternative supervised clustering method under evaluation.

Keywords: Supervised clustering, K-Means, K-Medoids

DOI: 10.3233/IDA-130618

Journal: Intelligent Data Analysis, vol. 17, no. 6, pp. 1023-1039, 2013