Multi-label feature selection with high-sparse personalized and low-redundancy shared common features

Yonghao Li, Liang Hu, Wanfu Gao

Abstract: Highlights•ESRFS can ensure high-sparse personalized features for each label and select low-redundancy shared features for all labels.•ESRFS can overcome the limitations of LASSO and L2,1-norms in multi-label problems.•ESRFS is introduced into the designed framework with the global solution.