Research map / Label-efficient and robust learning / Recognition and long-tail
Sparse PCA via L2,p-Norm Regularization for Unsupervised Feature Selection
Zhengxin Li, Feiping Nie, Jintang Bian, Danyang Wu, Xuelong Li
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use SPCAFS instead of the second-best method MCFS | K-means clustering on selected features · Imm40 | ACC: 5 percent improvement of ACC on average | Improved |
| use SPCAFS instead of the second-best method MCFS | K-means clustering on selected features · Imm40 | NMI: 3 percent improvement of NMI on average | Improved |
| select features with SPCAFS instead of using all features | K-means clustering · PalmData25 | ACC and NMI | Hurt |
| select features with SPCAFS instead of using all features | K-means clustering · Other data sets (Imm40, PIE, AR, SRBCTML, LEUML) | ACC and NMI | Improved |
| decrease p of the l2,p norm from 1 to 0.1 (ablation) | SPCAFS · Imm40 | ACC and NMI | Hurt |
| decrease p of the l2,p norm from 1 to 0.01 (ablation) | SPCAFS · SRBCTML | ACC and NMI | Mixed |
| vary regularization parameter gamma (ablation) | SPCAFS · Imm40 | ACC and NMI | No clear effect |
| vary reduced dimension m from 10 to 70 (ablation) | SPCAFS · Imm40 | ACC and NMI: 10 -> 70 | No clear effect |
Closest papers by meaning
- Unsupervised Feature Selection via Nonnegative Orthogonal Constrained Regularized Minimization (JMLR 2026 · similarity 0.88)
- Unsupervised Feature Selection with Structured Graph Optimization (AAAI 2016 · similarity 0.87)
- Unsupervised Discriminative Feature Selection With $\ell _{2,0}$ℓ2,0-Norm Constrained Sparse Projection (TPAMI 2025 · similarity 0.87)
- Structure Regularized Unsupervised Discriminant Feature Analysis (AAAI 2017 · similarity 0.86)
- A Probabilistic Derivation of LASSO and L12-Norm Feature Selections (AAAI 2019 · similarity 0.86)
- Efficient Sparse PCA via Block-Diagonalization (ICLR 2025 · similarity 0.85)
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.
