Research map / Learning theory and algorithms / Clustering
Inhomogeneous Hypergraph Clustering with Applications
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 the proposed projection for submodular hyperedge weights | InH clustering · Submodular hyperedges with |δ(e)| ≤ 7 | β approximation factor: β = 1, 1, 3/2, 2, 4, 6 for |δ(e)| = 2, 3, 4, 5, 6, 7, respectively | Helped |
| Complete unspecified hyperedge weights to satisfy submodularity | InH projection · Four-vertex example | projection feasibility with nonnegative edge weights | Helped |
| Set negative projected edge weights to zero | InH clustering · Hypergraphs with negative projected weights | empirical clustering performance | Helped |
| Use a homogeneous fan motif instead of inhomogeneous weights (ablation) | Florida Bay foodweb clustering · Florida Bay foodweb | hierarchical cluster recovery | Hurt |
| Use triangle motifs instead of the proposed four-species fan motif | Florida Bay foodweb clustering · Florida Bay foodweb | vertex coverage: 62 out of 128 vs 127 out of 128 | Hurt |
| Use InH-partition instead of AnchorsPartition | Ranking structure learning · Irish House of Parliament election dataset (2002) | overall party success | Helped |
| Use InH-partition instead of AnchorsPartition | Ranking structure learning · Irish House of Parliament election dataset (2002) | recovery of F.G. cluster | Hurt |
| Use InH-partition instead of AnchorsPartition | Ranking structure learning · Irish House of Parliament election dataset (2002) | recovery of Ind. cluster | Helped |
Closest papers by meaning
- A Unified Framework for Deep Hypergraph Clustering Beyond Homophily (ICML 2026 · similarity 0.88)
- Edge-Colored Clustering in Hypergraphs: Beyond Minimizing Unsatisfied Edges (ICML 2025 · similarity 0.88)
- Improved Algorithms for Overlapping and Robust Clustering of Edge-Colored Hypergraphs: An LP-Based Combinatorial Approach (NeurIPS 2025 · similarity 0.87)
- Optimal Graph Clustering without Edge Density Signals (NeurIPS 2025 · similarity 0.86)
- Hypergraph Learning for Unsupervised Graph Alignment via Optimal Transport (AAAI 2025 · similarity 0.85)
- Hierarchical Overlapping Clustering on Graphs: Cost Function, Algorithm and Scalability (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.