The Impact of Random Models on Clustering Similarity

01/23/2017
by   Alexander J. Gates, et al.
0

Clustering is a central approach for unsupervised learning. After clustering is applied, the most fundamental analysis is to quantitatively compare clusterings. Such comparisons are crucial for the evaluation of clustering methods as well as other tasks such as consensus clustering. It is often argued that, in order to establish a baseline, clustering similarity should be assessed in the context of a random ensemble of clusterings. The prevailing assumption for the random clustering ensemble is the permutation model in which the number and sizes of clusters are fixed. However, this assumption does not necessarily hold in practice; for example, multiple runs of K-means clustering returns clusterings with a fixed number of clusters, while the cluster size distribution varies greatly. Here, we derive corrected variants of two clustering similarity measures (the Rand index and Mutual Information) in the context of two random clustering ensembles in which the number and sizes of clusters vary. In addition, we study the impact of one-sided comparisons in the scenario with a reference clustering. The consequences of different random models are illustrated using synthetic examples, handwriting recognition, and gene expression data. We demonstrate that the choice of random model can have a drastic impact on the ranking of similar clustering pairs, and the evaluation of a clustering method with respect to a random baseline; thus, the choice of random clustering model should be carefully justified.

READ FULL TEXT
research
08/28/2012

Document Clustering Evaluation: Divergence from a Random Baseline

Divergence from a random baseline is a technique for the evaluation of d...
research
03/29/2018

On Hyperparameter Search in Cluster Ensembles

Quality assessments of models in unsupervised learning and clustering ve...
research
12/21/2022

Improving Narrative Relationship Embeddings by Training with Additional Inverse-Relationship Constraints

We consider the problem of embedding character-entity relationships from...
research
10/08/2018

Unique Metric for Health Analysis with Optimization of Clustering Activity and Cross Comparison of Results from Different Approach

In machine learning and data mining, Cluster analysis is one of the most...
research
12/23/2021

Ensemble Method for Cluster Number Determination and Algorithm Selection in Unsupervised Learning

Unsupervised learning, and more specifically clustering, suffers from th...
research
07/17/2012

Ensemble Clustering with Logic Rules

In this article, the logic rule ensembles approach to supervised learnin...
research
02/25/2015

Exploiting a comparability mapping to improve bi-lingual data categorization: a three-mode data analysis perspective

We address in this paper the co-clustering and co-classification of bili...

Please sign up or login with your details

Forgot password? Click here to reset