Research map / Learning theory and algorithms / Clustering
The Hyperspherical Geometry of Community Detection: Modularity as a Distance
Martijn Gösgens, Remco van der Hofstad, Nelly Litvak
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 |
|---|---|---|---|
| use CM meridian query instead of CM modularity | Louvain projection method · Karate club | correlation distance to ground truth: perfectly recovers the ground truth | Improved |
| use CM meridian query instead of CM modularity | Louvain projection method · EU-core | correlation distance to ground truth | Hurt |
| use CM meridian query instead of CM modularity | Louvain projection method · Dolphins, Political books, Football, Political blogs | correlation distance to ground truth | No clear effect |
| use wedge (common-neighbor) query vector instead of modularity vectors | Louvain projection method · Football | correlation distance to ground truth: 0.248π -> 0.186π | Improved |
| use wedge (common-neighbor) query vector instead of modularity vectors | Louvain projection method · Political blogs | correlation distance to ground truth | Hurt |
| set query latitude equal to the ground truth latitude (ablation) | Louvain on ER meridian, planted partition model · Planted partition model (20 communities of 20, degrees 6/4) | correlation distance between ground truth and candidate: best at query latitude 0.44π rather than at ground truth latitude | Hurt |
| use ER null model instead of CM null model for modularity vector (ablation) | modularity-based community detection · Six real-world networks | correlation distance to ground truth | Mixed |
| choose query vector closer to the ground truth in correlation distance | wedge vector vs modularity vectors · Six real-world networks | correlation distance to ground truth | No clear effect |
Closest papers by meaning
- Analysis of spectral clustering algorithms for community detection: the general bipartite setting (JMLR 2019 · similarity 0.88)
- Revisiting the Bethe-Hessian: Improved Community Detection in Sparse Heterogeneous Graphs (NeurIPS 2019 · similarity 0.88)
- MuMod: A Micro-Unit Connection Approach for Hybrid-Order Community Detection (AAAI 2020 · similarity 0.87)
- New Bounds on the Cohesion of Complete-link and Other Linkage Methods for Agglomerative Clustering (ICML 2024 · similarity 0.85)
- Learning Persistent Community Structures in Dynamic Networks via Topological Data Analysis (AAAI 2024 · similarity 0.85)
- Edge-Colored Clustering in Hypergraphs: Beyond Minimizing Unsatisfied Edges (ICML 2025 · similarity 0.85)
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.
