English

Merging $K$-means with hierarchical clustering for identifying general-shaped groups

Machine Learning 2017-12-27 v1 Computation Methodology

Abstract

Clustering partitions a dataset such that observations placed together in a group are similar but different from those in other groups. Hierarchical and KK-means clustering are two approaches but have different strengths and weaknesses. For instance, hierarchical clustering identifies groups in a tree-like structure but suffers from computational complexity in large datasets while KK-means clustering is efficient but designed to identify homogeneous spherically-shaped clusters. We present a hybrid non-parametric clustering approach that amalgamates the two methods to identify general-shaped clusters and that can be applied to larger datasets. Specifically, we first partition the dataset into spherical groups using KK-means. We next merge these groups using hierarchical methods with a data-driven distance measure as a stopping criterion. Our proposal has the potential to reveal groups with general shapes and structure in a dataset. We demonstrate good performance on several simulated and real datasets.

Keywords

Cite

@article{arxiv.1712.08786,
  title  = {Merging $K$-means with hierarchical clustering for identifying general-shaped groups},
  author = {Anna D. Peterson and Arka P. Ghosh and Ranjan Maitra},
  journal= {arXiv preprint arXiv:1712.08786},
  year   = {2017}
}

Comments

16 pages, 1 table, 9 figures; accepted for publication in Stat

R2 v1 2026-06-22T23:28:10.333Z