Research map / Graph learning / Graph algorithms and clustering
Information-theoretic Limits for Community Detection in Network Models
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 |
|---|---|---|---|
| Keep the within- versus between-community edge signal below (p-q)^2/[q(1-q)] ≤ 2 log 2/n - 4 log 2/n² | Stochastic Block Model · Stochastic Block Model | error probability: greater than or equal to $\frac{1}{2}$ | Hurt |
| Keep 2(cosh β - 1) ≤ 2 log 2/n - 4 log 2/n² | Exponential Random Graph Model · Exponential Random Graph Model | error probability: greater than or equal to $\frac{1}{2}$ | Hurt |
| Keep (4σ² + 1)^(-1-d/2) ||μ||₂² ≤ log 2/(2n) - log 2/n² | Latent Space Model · Latent Space Model | error probability: greater than or equal to $\frac{1}{2}$ | Hurt |
| Keep (p-q)^2/[q(1-q)] ≤ (n-2) log 2/(n²-n) | Dynamic Stochastic Block Model · Dynamic Stochastic Block Model | error probability: greater than or equal to $\frac{1}{2}$ | Hurt |
| Keep (4σ² + 1)^(-1-d/2) ||μ||₂² ≤ (n-2) log 2/[4(n² - n)] | Dynamic Latent Space Model · Dynamic Latent Space Model | error probability: greater than or equal to $\frac{1}{2}$ | Hurt |
| Keep (s+1)/(8m) ≤ 2^((n-2)/(n²-n))/n² | Directed Preferential Attachment Model · Directed Preferential Attachment Model | error probability: greater than or equal to $\frac{1}{2}$ | Hurt |
| Keep (s+1)²/[mp(1-p)] ≤ 2^(2(n-2)/n²)/n | Directed Small-world Model · Directed Small-world Model | error probability: greater than or equal to $\frac{1}{2}$ | Hurt |
Closest papers by meaning
- Harnessing Multiple Correlated Networks for Exact Community Recovery (NeurIPS 2024 · similarity 0.91)
- Exact Community Recovery under Side Information: Optimality of Spectral Algorithms (ICLR 2025 · similarity 0.89)
- Differentially private exact recovery for stochastic block models (ICML 2024 · similarity 0.89)
- Query-Limited Community Recovery in Stochastic Block Models (NeurIPS 2026 · similarity 0.88)
- Efficient Graph Matching for Correlated Stochastic Block Models (NeurIPS 2024 · similarity 0.87)
- Revisiting Instance-Optimal Cluster Recovery in the Labeled Stochastic Block Model (ICML 2025 · 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.