A RELIEF Based Feature Extraction Algorithm

RELIEF is considered one of the most successful algorithms for assessing the quality of features due to its simplicity and effectiveness. It has been recently proved that RELIEF is an online algorithm that solves a convex optimization problem with a marginbased objective function. Starting from this mathematical interpretation, we propose a novel feature extraction algorithm, referred to as LFE, as a natural generalization of RELIEF. LFE collects discriminant information through local learning, and is solved as an eigenvalue decomposition problem with a closed-form solution. A fast implementation is also derived. Experiments on synthetic and real-world data are presented. The results demonstrate that LFE performs significantly better than other feature extraction algorithms in terms of both computational efficiency and accuracy.