Feature selection via Non-convex constraint and latent representation learning with Laplacian embedding
作者：
Highlights：
• Calculate the similarity between pseudo-labels to keep complete sample information.
• The latent representation space is learned in latent feature space and data space.
• The latent representation contains the correlation of pseudo-labels.
• Latent feature space provides discriminative information to guide feature selection.
• Impose non-negative and l2,1-2-norm non-convex constraint on Q.
摘要
•Calculate the similarity between pseudo-labels to keep complete sample information.•The latent representation space is learned in latent feature space and data space.•The latent representation contains the correlation of pseudo-labels.•Latent feature space provides discriminative information to guide feature selection.•Impose non-negative and l2,1-2-norm non-convex constraint on Q.
论文关键词：Unsupervised feature selection,Latent representation learning,Pseudo-labels,Non-convex constraint
论文评审过程：Received 23 November 2021, Revised 27 May 2022, Accepted 14 July 2022, Available online 22 July 2022, Version of Record 31 July 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.118179
