Research map / Learning theory and algorithms / Clustering
Determining the Number of Communities in Degree-corrected Stochastic Block Models
Shujie Ma, Liangjun Su, Yichong Zhang
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 |
|---|---|---|---|
| increase c_h from 0.5 to 2.0 (ablation) | PLR2 · DCSBM S2, n=500, K0=3 | proportion correct K0: 1.000 -> 0.000 | Hurt |
| increase c_h from 0.5 to 2.0 (ablation) | PLR2 · DCSBM S2, n=500, K0=4 | proportion correct K0: 1.000 -> 0.825 | Hurt |
| vary c_h for sparse design S1 (ablation) | PLR2 · DCSBM S1 rho=3, n=500, K0=4 | proportion correct K0: 0.380 -> 0.370 | No clear effect |
| increase sample size from 500 to 1000 | PLR1 · DCSBM S1 rho=3, K0=4 | proportion correct K0: 0.380 -> 0.980 | Improved |
| increase sparsity parameter rho from 3 to 5 | PLR1 · DCSBM S1 n=500, K0=4 | proportion correct K0: 0.380 -> 0.985 | Improved |
| use PLR2 versus PLR1 at very sparse setting | PLR2 · DCSBM S1 K0=2, n=500, rho=0.5 | proportion correct K0: 0.71 -> 0.89 | Improved |
| use PLR1/PLR2 instead of LRBIC, NCV, ECV, BHMC at rho=3 | PLR1 · DCSBM S1 K0=4, n=500 | proportion correct K0: 0.38 vs close to zero | Improved |
| compare six methods under S2 where all B entries differ | PLR1/PLR2 · S2 designs, n=500 | proportion correct K0 | No clear effect |
Closest papers by meaning
- Achieving Optimal Misclassification Proportion in Stochastic Block Models (JMLR 2017 · similarity 0.91)
- Analysis of spectral clustering algorithms for community detection: the general bipartite setting (JMLR 2019 · similarity 0.91)
- Community Detection and Stochastic Block Models: Recent Developments (JMLR 2018 · similarity 0.91)
- Optimal Cluster Recovery in the Labeled Stochastic Block Model (NeurIPS 2016 · similarity 0.90)
- Recovering Unbalanced Communities in the Stochastic Block Model with Application to Clustering with a Faulty Oracle (NeurIPS 2023 · similarity 0.90)
- Revisiting Instance-Optimal Cluster Recovery in the Labeled Stochastic Block Model (ICML 2025 · similarity 0.89)
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.
