Revisiting Silhouette Aggregation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pavlopoulos, John, Vardakas, Georgios, Likas, Aristidis
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909229124681728
author Pavlopoulos, John
Vardakas, Georgios
Likas, Aristidis
author_facet Pavlopoulos, John
Vardakas, Georgios
Likas, Aristidis
contents Silhouette coefficient is an established internal clustering evaluation measure that produces a score per data point, assessing the quality of its clustering assignment. To assess the quality of the clustering of the whole dataset, the scores of all the points in the dataset are typically (micro) averaged into a single value. An alternative path, however, that is rarely employed, is to average first at the cluster level and then (macro) average across clusters. As we illustrate in this work with a synthetic example, the typical micro-averaging strategy is sensitive to cluster imbalance while the overlooked macro-averaging strategy is far more robust. By investigating macro-Silhouette further, we find that uniform sub-sampling, the only available strategy in existing libraries, harms the measure's robustness against imbalance. We address this issue by proposing a per-cluster sampling method. An experimental study on eight real-world datasets is then used to analyse both coefficients in two clustering tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2401_05831
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Revisiting Silhouette Aggregation
Pavlopoulos, John
Vardakas, Georgios
Likas, Aristidis
Machine Learning
Artificial Intelligence
Silhouette coefficient is an established internal clustering evaluation measure that produces a score per data point, assessing the quality of its clustering assignment. To assess the quality of the clustering of the whole dataset, the scores of all the points in the dataset are typically (micro) averaged into a single value. An alternative path, however, that is rarely employed, is to average first at the cluster level and then (macro) average across clusters. As we illustrate in this work with a synthetic example, the typical micro-averaging strategy is sensitive to cluster imbalance while the overlooked macro-averaging strategy is far more robust. By investigating macro-Silhouette further, we find that uniform sub-sampling, the only available strategy in existing libraries, harms the measure's robustness against imbalance. We address this issue by proposing a per-cluster sampling method. An experimental study on eight real-world datasets is then used to analyse both coefficients in two clustering tasks.
title Revisiting Silhouette Aggregation
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2401.05831