Abstract
Model selection is a major challenge in non-parametric clustering. There is no universally admitted way to evaluate clustering results for the obvious reason that no ground truth is available. The difficulty to find a universal evaluation criterion is a consequence of the ill-defined objective of clustering. In this perspective, clustering stability has emerged as a natural and model-agnostic principle: an algorithm should find stable structures in the data. If data sets are repeatedly sampled from the same underlying distribution, an algorithm should find similar partitions. However, stability alone is not well-suited to determine the number of clusters. For instance, it is unable to detect if the number of clusters is too small. We propose a new principle: a good clustering should be stable, and within each cluster, there should exist no stable partition. This principle leads to a novel clustering validation criterion based on between-cluster and within-cluster stability, overcoming limitations of previous stability-based methods. We empirically demonstrate the effectiveness of our criterion to select the number of clusters and compare it with existing methods. Code is available at https://github.com/FlorentF9/skstab.
A. Mourer and F. Forest—Equal contribution. Supported by ANRT CIFRE grants and Safran Aircraft Engines.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Balcan, M.F., Liang, Y.: Clustering under perturbation resilience. SIAM J. Comput. (2016)
Barton, T.: https://github.com/deric/clustering-benchmark
Ben-David, S.: Clustering-what both theoreticians and practitioners are doing wrong. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)
Ben-David, S., Pál, D., Simon, H.U.: Stability of k-means clustering. In: International Conference on Computational Learning Theory (2007)
Ben-David, S., Von Luxburg, U.: Relating clustering stability to properties of cluster boundaries. In: 21st Annual Conference on Learning Theory, COLT 2008 (2008)
Ben-David, S., Von Luxburg, U., Pál, D.: A sober look at clustering stability. In: International Conference on Computational Learning Theory (2006)
Ben-David, S., Reyzin, L.: Data stability in clustering: a closer look. Theoretical Computer Science (2014)
Ben-Hur, A., Elisseeff, A., Guyon, I.: A stability based method for discovering structure in clustered data. Pacific Symposium on Biocomputing (2002)
Bubeck, S., Meila, M., Luxburg, U.V.: How the initialization affects the stability of the k-means algorithm. ESAIM - Probability and Statistics (2012)
Caliński, T., Harabasz, J.: A dendrite method for cluster analysis. Commun. Stat.(1974)
Davies, D.L., Bouldin, D.W.: A cluster separation measure. IEEE Trans. Pattern Anal. Mach. Intell. (1979)
Demšar, J.: Statistical comparisons of classifiers over multiple data sets. J. Mach. Learn. Res. (2006)
Desgraupes, B.: ClusterCrit: clustering indices. CRAN Package (2013)
Dunn, J.C.: Well-Separated clusters and optimal fuzzy partitions. J. Cybern. (1974)
Falasconi, M., Gutierrez, A., Pardo, M., Sberveglieri, G., Marco, S.: A stability based validity method for fuzzy clustering. Pattern Recogn. (2010)
Fang, Y., Wang, J.: Selection of the number of clusters via the bootstrap method. Comput. Stat. Data Anal. 56(3), 468–477 (2012)
Gagolewski, M., Bartoszuk, M., Cena A.G.: A new, fast, and outlier-resistant hierarchical clustering algorithm (2016)
Hamerly, G., Elkan, C.: Learning the k in k-means. In: NIPS (2004)
Hennig, C.: Cluster-wise assessment of cluster stability. Comput. Stat. Data Anal. 52(1), 258–271 (2007)
Hess, S., Duivesteijn, W.: K is the magic number - inferring the number of clusters through nonparametric concentration inequalities. In: EMCL-PKDD (2019)
Hofmeyr, D.P.: Degrees of freedom and model selection for k-means clustering. arXiv preprint arXiv:1806.02034 (2018)
Lange, T., Roth, V., Braun, M.L., Buhmann, J.M.: Stability-based validation of clustering solutions. Neural Comput. (2004)
Maechler, M., Rousseeuw, P., Struyf, A., Hubert, M., et al.: Package ‘cluster’ (2013)
Meila, M.: How to tell when a clustering is (approximately) correct using convex relaxations. In: Advances in Neural Information Processing Systems (2018)
Möller, U., Radke, D.: A cluster validity approach based on nearest-neighbor resampling. In: Proceedings - International Conference on Pattern Recognition (2006)
Pelleg, D., Moore, A.: X-means: extending k-means with efficient estimation of the number of clusters. In: International Conference on Machine Learning (2000)
Ray, S., Turi, R.: Determination of number of clusters in k-means clustering and application in colour image segmentation. In: Proceedings of the 4th International Conference on Advances in Pattern Recognition and Digital Techniques (1999)
Rousseeuw, P.J.: Silhouettes: A graphical aid to the interpretation and validation of cluster analysis. J. Comput. Appl. Math. (1987)
Shamir, O., Tishby, N.: Cluster stability for finite samples. In: Advances in Neural Information Processing Systems (2007)
Smith, S.P., Dubes, R.: Stability of a hierarchical clustering. Pattern Recogn. (1980)
Strauss, J.S., Bartko, J.J., Carpenter, W.T.: The use of clustering techniques for the classification of psychiatric patients. British J. Psychiatry (1973)
Tibshirani, R., Walther, G., Hastie, T.: Estimating the number of clusters in a data set via the gap statistic. J. Royal Stat. Soc. Ser. B (2001)
Vijayaraghavan, A., Dutta, A., Wang, A.: Clustering stable instances of euclidean k-means. In: Advances in Neural Information Processing Systems (2017)
Von Luxburg, U.: Clustering stability: an overview. Found. Trends® Mach. Learn. (2010)
Yeung, K.Y., Haynor, D.R., Ruzzo, W.L.: Validating clustering for gene expression data. Bioinformatics (2001)
Zhao, Q., Xu, M., Fränti, P.: Extending external validity measures for determining the number of clusters. Intell. Syst. Design Appl. (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Mourer, A., Forest, F., Lebbah, M., Azzag, H., Lacaille, J. (2023). Selecting the Number of Clusters K with a Stability Trade-off: An Internal Validation Criterion. In: Kashima, H., Ide, T., Peng, WC. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2023. Lecture Notes in Computer Science(), vol 13935. Springer, Cham. https://doi.org/10.1007/978-3-031-33374-3_17
Download citation
DOI: https://doi.org/10.1007/978-3-031-33374-3_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-33373-6
Online ISBN: 978-3-031-33374-3
eBook Packages: Computer ScienceComputer Science (R0)