Ensemble- and Distance-Based Feature Ranking for Unsupervised Learning
This work addresses the problem of effectively ranking features without labeled data for machine learning practitioners, offering incremental improvements over existing unsupervised feature selection techniques.
This paper introduces two new methods for unsupervised feature ranking: ensemble-based scores (Genie3, RandomForest) derived from predictive clustering trees and URelief, an unsupervised extension of the Relief algorithm. Across 26 benchmark datasets and 5 baselines, Genie3 (using extra trees) and URelief both outperformed existing methods, with Genie3 achieving the best overall predictive power from top-ranked features.
In this work, we propose two novel (groups of) methods for unsupervised feature ranking and selection. The first group includes feature ranking scores (Genie3 score, RandomForest score) that are computed from ensembles of predictive clustering trees. The second method is URelief, the unsupervised extension of the Relief family of feature ranking algorithms. Using 26 benchmark data sets and 5 baselines, we show that both the Genie3 score (computed from the ensemble of extra trees) and the URelief method outperform the existing methods and that Genie3 performs best overall, in terms of predictive power of the top-ranked features. Additionally, we analyze the influence of the hyper-parameters of the proposed methods on their performance, and show that for the Genie3 score the highest quality is achieved by the most efficient parameter configuration. Finally, we propose a way of discovering the location of the features in the ranking, which are the most relevant in reality.