Research map / Learning theory and algorithms / Clustering
Revisiting the Bethe-Hessian: Improved Community Detection in Sparse Heterogeneous Graphs
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 r=ζ instead of r=√(cΦ) in the Bethe-Hessian | Bethe-Hessian community detection · Synthetic sparse heterogeneous graphs with power-law degree variation | overlap | Helped |
| Use r=ζ instead of r=√(cΦ) in the Bethe-Hessian | Bethe-Hessian community detection · Synthetic homogeneous-degree graphs | overlap | No clear effect |
| Use r=ζ instead of r=√(cΦ) | Bethe-Hessian · Karate | overlap: 1.00 -> 1.00 | No clear effect |
| Use r=ζ instead of r=√(cΦ) | Bethe-Hessian · Dolphins | overlap: 0.87 -> 0.97 | Helped |
| Use r=ζ instead of r=√(cΦ) | Bethe-Hessian · Polbooks | overlap: 0.74 -> 0.77 | Helped |
| Use r=ζ instead of r=√(cΦ) | Bethe-Hessian · Football | overlap: 0.92 -> 0.92 | No clear effect |
| Use r=ζ instead of r=√(cΦ) | Bethe-Hessian · Polblogs | overlap: 0.32 -> 0.91 | Helped |
| Use r=ζ instead of r=√(cΦ) | Bethe-Hessian · Mail | modularity: 0.40 -> 0.50 | Helped |
| Use r=ζ instead of r=√(cΦ) | Bethe-Hessian · Facebook | modularity: 0.48 -> 0.77 | Helped |
| Use r=ζ instead of r=√(cΦ) | Bethe-Hessian · Power grid | modularity: 0.61 -> 0.92 | Helped |
| Use r=ζ instead of r=√(cΦ) | Bethe-Hessian · Nutella | modularity: 0.15 -> 0.34 | Helped |
| Use r=ζ instead of r=√(cΦ) | Bethe-Hessian · Wikipedia | modularity: 0.18 -> 0.21 | Helped |
Closest papers by meaning
- Community detection in sparse time-evolving graphs with a dynamical Bethe-Hessian (NeurIPS 2020 · similarity 0.92)
- Structure-Aware Spectral Sparsification via Uniform Edge Sampling (NeurIPS 2025 · similarity 0.87)
- Equivalence between Graph Spectral Clustering and Column Subset Selection (Student Abstract) (AAAI 2024 · similarity 0.87)
- Pass-Efficient Algorithms for Graph Spectral Clustering (Student Abstract) (AAAI 2024 · similarity 0.87)
- Optimal Graph Clustering without Edge Density Signals (NeurIPS 2025 · similarity 0.86)
- Revisiting Self-Supervised Heterogeneous Graph Learning from Spectral Clustering Perspective (NeurIPS 2024 · 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.