Research map / Learning theory and algorithms / Clustering
Simultaneous Clustering and Estimation of Heterogeneous Graphical Models
Botao Hao, Will Wei Sun, Yufeng Liu, Guang Cheng
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 |
|---|---|---|---|
| replace K-means then JGL two-stage with simultaneous clustering and estimation (SCAN) | clustering + graphical model estimation · Simulation Model 1 (regular network) | clustering error: 0.166 -> 0.071 | Improved |
| replace K-means then JGL two-stage with SCAN | clustering + graphical model estimation · Simulation Model 2 (regular network) | clustering error: 0.210 -> 0.058 | Improved |
| replace K-means then JGL two-stage with SCAN | clustering + graphical model estimation · Simulation Model 4 (power-law network) | clustering error: 0.331 -> 0.283 | Improved |
| replace K-means then JGL two-stage with SCAN | clustering + graphical model estimation · Simulation Model 7 (chain network) | clustering error: 0.277 -> 0.231 | Improved |
| share information across precision matrices (SCAN) instead of estimating each separately (Zhou et al. 2009) | precision matrix estimation · Simulation Model 1 (regular network) | precision matrix error: 10.458 -> 7.620 | Improved |
| share information across precision matrices (SCAN) instead of Zhou et al. (2009) | precision matrix estimation · Simulation Model 4 (power-law network) | precision matrix error: 50.945 -> 48.845 | Improved |
| share information across precision matrices (SCAN) instead of Zhou et al. (2009) | false positive rate of edge selection · Simulation Model 1 (regular network) | false positive rate: 0.107 -> 0.022 | Improved |
| increase cluster separation mu from 0.7 to 0.9 | SCAN · Simulation Models 7-9 (chain network) | clustering error: 0.231 -> 0.098 | Improved |
| use SCAN instead of K-means + JGL | clustering + graphical model estimation · Glioblastoma gene expression | clustering error: 0.262 -> 0.222 | Improved |
| estimate each cluster precision matrix separately (Zhou et al. 2009) instead of K-means + JGL | clustering + graphical model estimation · Glioblastoma gene expression | clustering error: 0.262 -> 0.336 | Hurt |
| run K-means then JGL instead of K-means alone | clustering · Simulation Models 1-9 | clustering error: 0.166 -> 0.166 | No clear effect |
Closest papers by meaning
- High-Dimensional Inference for Cluster-Based Graphical Models (JMLR 2020 · similarity 0.90)
- Joint Structural Estimation of Multiple Graphical Models (JMLR 2016 · similarity 0.88)
- Speeding Up Latent Variable Gaussian Graphical Model Estimation via Nonconvex Optimization (NeurIPS 2017 · similarity 0.87)
- Heterogeneous Sufficient Dimension Reduction and Subspace Clustering (ICML 2025 · similarity 0.86)
- Achieving Optimal Clustering in Gaussian Mixture Models with Anisotropic Covariance Structures (NeurIPS 2024 · similarity 0.86)
- A Generic Family of Graphical Models: Diversity, Efficiency, and Heterogeneity (ICML 2025 · similarity 0.86)
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.
