DiscoVars: A New Data Analysis Perspective -- Application in Variable Selection for Clustering
This work addresses variable selection for clustering, which is important in scenarios like remote sensing where data collection costs are high, but it appears incremental as it builds on existing unsupervised methods.
The authors tackled the problem of variable selection for clustering by proposing a new methodology that creates dependency networks among variables and ranks them using graph centrality measures, resulting in a tool that selects top-n variables as a candidate subset for further learning tasks.
We present a new data analysis perspective to determine variable importance regardless of the underlying learning task. Traditionally, variable selection is considered an important step in supervised learning for both classification and regression problems. The variable selection also becomes critical when costs associated with the data collection and storage are considerably high for cases like remote sensing. Therefore, we propose a new methodology to select important variables from the data by first creating dependency networks among all variables and then ranking them (i.e. nodes) by graph centrality measures. Selecting Top-$n$ variables according to preferred centrality measure will yield a strong candidate subset of variables for further learning tasks e.g. clustering. We present our tool as a Shiny app which is a user-friendly interface development environment. We also extend the user interface for two well-known unsupervised variable selection methods from literature for comparison reasons.