Research map / Graph learning / Graph algorithms and clustering
Robustness of Community Detection to Random Geometric Perturbations
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 |
|---|---|---|---|
| Increase γ, narrowing the geometric kernel and weakening its perturbation | Second adjacency eigenvector community detection · Synthetic SBM with geometric perturbation, N=2000 | correlation with community vector: 0 -> 0.9 | Helped |
| Use γ=50 instead of a larger γ (ablation) | Second adjacency eigenvector community detection · Synthetic SBM with geometric perturbation, N=2000 | separation of the second eigenvalue from the geometric spectrum | Hurt |
| Set p2=1.5% (ablation) | Second adjacency eigenvector community detection · Synthetic SBM with geometric perturbation | separation of the second eigenvalue from the bulk | Hurt |
| Set p2=4% (ablation) | Second adjacency eigenvector community detection · Synthetic SBM with geometric perturbation | separation of the second eigenvalue from the bulk | Helped |
| Increase the community signal until λ2/μ1 grows without bound | Second adjacency eigenvector community detection · Two-community SBM with geometric perturbation | correlation with community vector | Helped |
Closest papers by meaning
- On the Robustness of Spectral Algorithms for Semirandom Stochastic Block Models (NeurIPS 2024 · similarity 0.92)
- Exact Community Recovery under Side Information: Optimality of Spectral Algorithms (ICLR 2025 · similarity 0.90)
- Efficient Graph Matching for Correlated Stochastic Block Models (NeurIPS 2024 · similarity 0.87)
- Differentially private exact recovery for stochastic block models (ICML 2024 · similarity 0.87)
- Query-Limited Community Recovery in Stochastic Block Models (NeurIPS 2026 · similarity 0.87)
- Optimal community detection in dense bipartite graphs (NeurIPS 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.