Semi-supervised Feature Selection with Adaptive Discriminant Analysis

EasyChair Preprint 740

Abstract

In this paper, we propose a novel Adaptive Discriminant Analysis for semi-supervised feature selection, namely SADA. Instead of computing fixed similarities before performing feature selection, SADA simultaneously learns an adaptive similarity matrix S and a projection matrix W with an iterative method. In each iteration, S is computed from the projected distance with the learned W and W is computed with the learned S. Therefore, SADA can learn better projection matrix W by weakening the effect of noise features with the adaptive similarity matrix. Experimental results on 4 data sets show the superiority of SADA compared to 5 supervised feature selection methods.

Keyphrases: Adaptive Discriminant Analysis, Learning Systems, feature selection, robustness, semi-supervised feature selection, sparse matrices

@booklet{EasyChair:740,
  author    = {Weichan Zhong and Xiaojun Chen and Guowen Yuan and Yiqin Li and Feiping Nie},
  title     = {Semi-supervised Feature Selection with Adaptive Discriminant Analysis},
  howpublished = {EasyChair Preprint 740},
  year      = {EasyChair, 2019}}