Active Sampling: An Effective Approach to Feature Selection
Huan Liu, Hongjun Lü, Lei Yu · 2003
Feature selection is frequently used in data preprocessing for data mining. It decreases number of features, removes irrelevant or noisy data, and increases mining performance such as predictive accuracy and comprehensibility. This work investigates active sampling in feature selection in a filter model setting. Three versions of active sampling are proposed and empirically evaluated: two employ class information and the other utilizes feature variance. They are applied to a widely used, efficient feature selection algorithm Relief. In comparison with random sampling, we conduct extensive experiments with benchmark data sets.