AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Unsupervised Feature Selection via Nonnegative Orthogonal Constrained Regularized Minimization

Yan Li, Defeng Sun, Liping Zhang

JMLR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Frobenius-norm overfitting-prevention regularization (gamma > 0) (ablation)NOCRM · 10 datasets meanACC: 51.9 -> 55.3Improved
add Frobenius-norm overfitting-prevention regularization (gamma > 0) (ablation)NOCRM · 10 datasets meanNMI: 63.7 -> 66.3Improved
add Frobenius-norm regularization (ablation)NOCRM · lungACC: 65.4 -> 82.4Improved
add Frobenius-norm regularization (ablation)NOCRM · warpPIE10PACC: 43.1 -> 50.1Improved
add Frobenius-norm regularization (ablation)NOCRM · IsoletACC: 65.8 -> 65.8No clear effect
perturb the number of clusters by minus 1 or 5 / plus 1 or 5 (ablation)NOCRM · 10 datasets meanACC: 55.3 -> 55.5 (minus), 55.6 (plus)No clear effect
use NOCRM instead of NDFSunsupervised feature selection · 10 datasets meanACC: 49.7 -> 55.3Improved
use NOCRM instead of the best baseline MCFSunsupervised feature selection · 10 datasets meanACC: 50.5 -> 55.3Improved
use NOCRM instead of NDFSunsupervised feature selection · 10 datasets meanNMI: 61.2 -> 66.3Improved
use NOCRM instead of Maxvarunsupervised feature selection · 10 datasets meanJaccard stability: 74.2% -> 87.6%Improved
use NOCRM instead of NDFSunsupervised feature selection · 10 datasets mean, 25% noiseACC retention ratio: 62.0% -> 80.8%Improved
use NOCRM instead of NDFS/UDFS/UDPFSunsupervised feature selection · 9 TumorsACC: 44.1 vs UDPFS 46.8Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy