Self-Paced Probabilistic Principal Component Analysis For Data With Outliers
Bowen Zhao, Xi Xiao, Wanpeng Zhang, Bin Zhang, Guojun Gan, Shutao Xia
Abstract
Principal Component Analysis (PCA) is a popular tool for dimension reduction and feature extraction in data analysis. Probabilistic PCA (PPCA) extends the standard PCA by using a probabilistic model. However, both standard PCA and PPCA are not robust, as they are sensitive to outliers. To alleviate this problem, we propose a novel method called Self-Paced Probabilistic Principal Component Analysis (SP-PPCA) by introducing the Self-Paced Learning mechanism into PPCA. Furthermore, we design the corresponding optimization algorithm based on an alternative search strategy and an expectation-maximization algorithm, so that SP-PPCA uses an iterative procedure to find the optimal projection vectors and filter out outliers. Experiments on both synthetic data and real data demonstrate that SP-PPCA is more robust than the baselines.
BibTeX
@inproceedings{icassp2020_selfpacedprobabi,
title = {Self-Paced Probabilistic Principal Component Analysis For Data With Outliers},
author = {Bowen Zhao and Xi Xiao and Wanpeng Zhang and Bin Zhang and Guojun Gan and Shutao Xia},
booktitle = {ICASSP 2020},
year = {2020}
}