Research map / Learning theory and algorithms / Clustering
Simple and Scalable Sparse k-means Clustering via Feature Ranking
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 feature ranking and shared top-feature truncation in place of standard k-means | k-means clustering · 10 benchmark datasets | NMI: SKFR1 gives the best result in terms of NMI for 9 of the 10 datasets. | Helped |
| Use SKFR1 rather than k-means++ | clustering mouse protein expression · Control mice | mixed nodes: 11 -> 4 | Helped |
| Use SKFR1 rather than k-means++ | clustering mouse protein expression · Control mice | total mixed: 164 -> 67 | Helped |
| Use SKFR1 rather than k-means++ | clustering mouse protein expression · Trisomic mice | mixed nodes: 9 -> 3 | Helped |
| Use SKFR1 rather than k-means++ | clustering mouse protein expression · Trisomic mice | total mixed: 152 -> 64 | Helped |
| Use cluster-specific feature rankings | SKFR2 · simulated clusters with different informative feature subsets | ARI | Helped |
| Apply SKFR1 with imputation to partially observed data | sparse k-means clustering · simulated data with 10% missing entries | ARI | Helped |
| Use feature ranking rather than SKM's feature weighting | feature selection in sparse clustering · simulated sparse clustering | false positive rate: SKFR1: 0.0, 0.025, 0.028, 0.016, 0.012, 0.009; SKM: 0.10, 0.05, 0.044, 0.068, 0.059, 0.039 | Helped |
| Use the robust median-based SKFR modification | SKFR · simulated data with outliers | ARI | Mixed |
Closest papers by meaning
- Sparse Embedded $k$-Means Clustering (NeurIPS 2017 · similarity 0.91)
- The Complexity of k-Means Clustering when Little is Known (ICML 2022 · similarity 0.91)
- Simple, Scalable and Effective Clustering via One-Dimensional Projections (NeurIPS 2023 · similarity 0.90)
- Improved Learning-augmented Algorithms for k-means and k-medians Clustering (ICLR 2023 · similarity 0.90)
- Efficient Clustering Based On A Unified View Of $K$-means And Ratio-cut (NeurIPS 2020 · similarity 0.89)
- Statistically Optimal $K$-means Clustering via Nonnegative Low-rank Semidefinite Programming (ICLR 2024 · similarity 0.87)
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.