Robust graph regularized unsupervised feature selection
作者：
Highlights：
• We propose a robust graph regularized unsupervised feature selection model.
• We introduce an l1-norm based graph to preserve the local structure of data.
• Feature reconstruction term is regularized by l2, 1-norm for robustness to outliers.
• An efficient solver is developed to solve the proposed optimization problem.
• Experiments confirmed our method outperforms other state-of-the-art methods.
摘要
•We propose a robust graph regularized unsupervised feature selection model.•We introduce an l1-norm based graph to preserve the local structure of data.•Feature reconstruction term is regularized by l2, 1-norm for robustness to outliers.•An efficient solver is developed to solve the proposed optimization problem.•Experiments confirmed our method outperforms other state-of-the-art methods.
论文关键词：Unsupervised feature selection,Local geometric structure,Graph regularization,Similarity preservation
论文评审过程：Received 11 September 2017, Revised 26 November 2017, Accepted 27 November 2017, Available online 2 December 2017, Version of Record 22 December 2017.
论文官网地址：https://doi.org/10.1016/j.eswa.2017.11.053
