Classification Recouvrante Bas\'ee sur les M\'ethodes \`a Noyau

TL;DR

This paper introduces OKM-K, a kernel-based extension of the overlapping k-means algorithm, which improves clustering performance on datasets with overlapping clusters by leveraging high-dimensional feature spaces.

Contribution

It proposes a novel kernel-based method, OKM-K, that enhances overlapping clustering by mapping data into high-dimensional spaces using Mercer kernels.

Findings

OKM-K outperforms OKM on overlapping datasets.

Kernel methods improve cluster separability.

Empirical results demonstrate enhanced clustering accuracy.

Abstract

Overlapping clustering problem is an important learning issue in which clusters are not mutually exclusive and each object may belongs simultaneously to several clusters. This paper presents a kernel based method that produces overlapping clusters on a high feature space using mercer kernel techniques to improve separability of input patterns. The proposed method, called OKM-K(Overlapping $k$-means based kernel method), extends OKM (Overlapping $k$-means) method to produce overlapping schemes. Experiments are performed on overlapping dataset and empirical results obtained with OKM-K outperform results obtained with OKM.