RECORD
Cluster Metric Sensitivity to Irrelevant Features
Machine Learning · Submitted 19 Feb 2024
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim As such the Silhouette Coefficient and the Davies-Bouldin score are good candidates for optimising feature selection in unsupervised clustering tasks.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Clustering algorithms are used extensively in data analysis for data exploration and discovery. Technological advancements lead to continually growth of data in terms of volume, dimensionality and complexity. This provides great opportunities in data analytics as the data can be interrogated for many different purposes. This however leads challenges, such as identification of relevant features for a given task. In supervised tasks, one can utilise a number of methods to optimise the input features for the task objective (e.g. classification accuracy). In unsupervised problems, such tools are not readily available, in part due to an inability to quantify feature relevance in unlabeled tasks. In this paper, we investigate the sensitivity of clustering performance noisy uncorrelated variables iteratively added to baseline datasets with well defined clusters. We show how different types of irrelevant variables can impact the outcome of a clustering result from $k$-means in different ways. We observe a resilience to very high proportions of irrelevant features for adjusted rand index (ARI) and normalised mutual information (NMI) when the irrelevant features are Gaussian distributed. For Uniformly distributed irrelevant features, we notice the resilience of ARI and NMI is dependent on the dimensionality of the data and exhibits tipping points between high scores and near zero. Our results show that the Silhouette Coefficient and the Davies-Bouldin score are the most sensitive to irrelevant added features exhibiting large changes in score for comparably low proportions of irrelevant features regardless of underlying distribution or data scaling. As such the Silhouette Coefficient and the Davies-Bouldin score are good candidates for optimising feature selection in unsupervised clustering tasks.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Clustering algorithms are used extensively in data analysis for data exploration and discovery. | background 1.00 | 0.03 | 0.01 | asserted 1.00 |
| s1 | Technological advancements lead to continually growth of data in terms of volume, dimensionality and complexity. | background 1.00 | 0.03 | 0.01 | asserted 1.00 |
| s2 | This provides great opportunities in data analytics as the data can be interrogated for many different purposes. | background 1.00 | 0.03 | 0.01 | asserted 0.96 |
| s3 | This however leads challenges, such as identification of relevant features for a given task. | background 0.97 | 0.04 | 0.02 | asserted 0.98 |
| s4 | In supervised tasks, one can utilise a number of methods to optimise the input features for the task objective (e.g. classification accuracy). | background 0.99 | 0.04 | 0.01 | hedged possibility 0.63 |
| s5 | In unsupervised problems, such tools are not readily available, in part due to an inability to quantify feature relevance in unlabeled tasks. | gap 0.84 | 0.04 | 0.02 | asserted 0.97 |
| s6 | In this paper, we investigate the sensitivity of clustering performance noisy uncorrelated variables iteratively added to baseline datasets with well defined clusters. | contribution 0.96 | 0.88 | 0.04 | asserted 0.90 |
| s7 | We show how different types of irrelevant variables can impact the outcome of a clustering result from $k$-means in different ways. | contribution 0.87 | 0.90 | 0.06 | asserted 1.00 |
| s8 | We observe a resilience to very high proportions of irrelevant features for adjusted rand index (ARI) and normalised mutual information (NMI) when the irrelevant features are Gaussian distributed. | result 1.00 | 0.94 | 0.11 | asserted 1.00 |
| s9 | For Uniformly distributed irrelevant features, we notice the resilience of ARI and NMI is dependent on the dimensionality of the data and exhibits tipping points between high scores and near zero. | result 1.00 | 0.95 | 0.07 | asserted 0.99 |
| s10 | Our results show that the Silhouette Coefficient and the Davies-Bouldin score are the most sensitive to irrelevant added features exhibiting large changes in score for comparably low proportions of irrelevant features regardless of underlying distribution or data scaling. | result 0.99 | 0.95 | 0.72 | asserted 1.00 |
| s11 | As such the Silhouette Coefficient and the Davies-Bouldin score are good candidates for optimising feature selection in unsupervised clustering tasks. | interpretation 0.99 | 0.73 | 0.74 | hedged possibility 0.65 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Clustering algorithms are used extensively in data analysis for data exploration and discovery. Technological advancements lead to continually growth of data in terms of volume, dimensionality and complexity. This provides great opportunities in data analytics as the data can be interrogated for many different purposes. This however leads challenges, such as identification of relevant features for a given task. In supervised tasks, one can utilise a number of methods to optimise the input features for the task objective (e.g. classification accuracy). In unsupervised problems, such tools are not readily available, in part due to an inability to quantify feature relevance in unlabeled tasks. In this paper, we investigate the sensitivity of clustering performance noisy uncorrelated variables iteratively added to baseline datasets with well defined clusters. We show how different types of irrelevant variables can impact the outcome of a clustering result from $k$-means in different ways. We observe a resilience to very high proportions of irrelevant features for adjusted rand index (ARI) and normalised mutual information (NMI) when the irrelevant features are Gaussian distributed. For Uniformly distributed irrelevant features, we notice the resilience of ARI and NMI is dependent on the dimensionality of the data and exhibits tipping points between high scores and near zero. Our results show that the Silhouette Coefficient and the Davies-Bouldin score are the most sensitive to irrelevant added features exhibiting large changes in score for comparably low proportions of irrelevant features regardless of underlying distribution or data scaling. As such the Silhouette Coefficient and the Davies-Bouldin score are good candidates for optimising feature selection in unsupervised clustering tasks.
Human review
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.