Research map / Graph learning / Graph algorithms and clustering
Graph Clustering: Block-models and model free results
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 |
|---|---|---|---|
| Model-free stability guarantee via PFM-based bound (Theorem 4) with spectral clustering output, applied to PFM-generated graphs | PFM datasets (n=10000, K=5) · Simulated PFM graphs | stability condition delta <= delta0 (guarantee holds) | Mixed |
| Use SBM-based bound (Theorem 9) instead of PFM-based bound (Theorem 4) for the same data (ablation) | SBM guarantees on LFR and other datasets · LFR simulated matrix; Political Blogs | whether delta <= delta0 can be satisfied (stability guarantee) | Hurt |
| Use the Proposition 10 improved bound delta_Y (using Y and M-hat) in place of delta in Theorem 4 | PFM model-free guarantee · Theoretical | bound tightness | Helped |
| Replace the Davis-Kahan based bound with the alternative result derived from Theorem 3 of [20] | PFM model-free guarantee · Theoretical | constant in error bound: 128 K eps^2/(eigengap)^2 vs. original bound | Helped |
| Smoothing the graph by taking powers of its adjacency matrix (A = (A^T A)^3 for Political Blogs) (ablation) | Political Blogs graph · Political Blogs | stability (delta / delta0) of clustering | Helped |
Closest papers by meaning
- Multi-View Stochastic Block Models (ICML 2024 · similarity 0.91)
- Optimal Graph Clustering without Edge Density Signals (NeurIPS 2025 · similarity 0.90)
- Revisiting Instance-Optimal Cluster Recovery in the Labeled Stochastic Block Model (ICML 2025 · similarity 0.89)
- From Your Block to Our Block: How to Find Shared Structure Between Stochastic Block Models over Multiple Graphs (AAAI 2025 · similarity 0.88)
- On the Robustness of Spectral Algorithms for Semirandom Stochastic Block Models (NeurIPS 2024 · similarity 0.88)
- Efficient Graph Matching for Correlated Stochastic Block Models (NeurIPS 2024 · similarity 0.88)
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.