A latent variable pairwise classification model of a clustering ensemble

Authors:
Vladimir Berikov
Affiliations:
Sobolev Institute of mathematics, Novosibirsk State University, Russia
Venue:
MCS'11 Proceedings of the 10th international conference on Multiple classifier systems
Year:
2011

Citing 9
Cited 1

Random Forests

Machine Learning
Cluster ensembles --- a knowledge reuse framework for combining multiple partitions

The Journal of Machine Learning Research
Combining Pattern Classifiers: Methods and Algorithms

Combining Pattern Classifiers: Methods and Algorithms
Analysis of Consensus Partition in Cluster Ensemble

ICDM '04 Proceedings of the Fourth IEEE International Conference on Data Mining
Moderate diversity for better cluster ensembles

Information Fusion
To combine steady-state genetic algorithm and ensemble learning for data clustering

Pattern Recognition Letters
Adaptive cluster ensemble selection

IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
Data clustering: 50 years beyond K-means

Pattern Recognition Letters
LCE

Bioinformatics

Weighted ensemble of algorithms for complex data clustering

Pattern Recognition Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper addresses some theoretical properties of clustering ensembles. We consider the problem of cluster analysis from pattern recognition point of view. A latent variable pairwise classification model is proposed for studying the efficiency (in terms of "error probability") of the ensemble. The notions of stability, homogeneity and correlation between ensemble elements are introduced. An upper bound for misclassification probability is obtained. Numerical experiment confirms potential usefulness of the suggested ensemble characteristics.