Joint feature representation and classification via adaptive graph semi-supervised nonnegative matrix factorization
作者：
Highlights：
• Our proposed framework can achieve the feature representation and classification task simultaneously.
• We integrate the matrix factorization, adaptive graph learning and label propagation into a unified framework.
• In our proposed model, we add a local constraint into adaptive graph learning, which can exploit the locality of data adequately.
• An iterative optimization algorithm is used to solve the objective function.
摘要
•Our proposed framework can achieve the feature representation and classification task simultaneously.•We integrate the matrix factorization, adaptive graph learning and label propagation into a unified framework.•In our proposed model, we add a local constraint into adaptive graph learning, which can exploit the locality of data adequately.•An iterative optimization algorithm is used to solve the objective function.
论文关键词：Feature representation,Nonnegative matrix factorization,Adaptive graph,Label propagation,Classification
论文评审过程：Received 24 July 2019, Revised 24 May 2020, Accepted 22 August 2020, Available online 27 August 2020, Version of Record 9 September 2020.
论文官网地址：https://doi.org/10.1016/j.image.2020.115984
