Research map / Graph learning / Graph self-supervised learning
SuperHype: Hypergraph Generation via Graph-Superposition Decomposition
Lucas Gantes, Abele Mălan, Roberto Gheda, Robert Birke, Lydia Chen
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 |
|---|---|---|---|
| graph-superposition representation (SuperHype) instead of bipartite representation | HYGENE · SBM | validity-uniqueness-novelty %: 63% -> 88.3% | Improved |
| graph-superposition representation (SuperHype) instead of bipartite representation | HYGENE · Tree | validity-uniqueness-novelty %: 79.2% -> 90% | Improved |
| graph-superposition representation (SuperHype) instead of bipartite representation | HYGENE · Ego | validity-uniqueness-novelty %: 95.6% -> 50.6% | Hurt |
| graph-superposition representation (SuperHype) instead of bipartite representation | HYGENE · SBM | node degree Wasserstein distance: 1.7 -> 6.8e-1 | Improved |
| graph-superposition representation (SuperHype) instead of bipartite representation | HYGENE · Tree | spectral MMD: 7.9e-3 -> 3.1e-4 | Improved |
| graph-superposition representation (SuperHype) instead of bipartite representation | HYGENE · Erdos-Renyi | spectral MMD: 4.7e-3 -> 9.2e-4 | Improved |
| graph-superposition representation (SuperHype) instead of bipartite representation | HYGENE · ModelNet40 Bookshelf | node degree Wasserstein distance: 8.2 -> 3.2 | Improved |
| graph-superposition representation (SuperHype) instead of bipartite representation | HyperPLR · ModelNet40 Bookshelf | spectral MMD: 1.9e-3 -> 2.9e-2 | Hurt |
| graph-superposition representation (SuperHype) instead of bipartite representation | HyperPLR · SBM | validity-uniqueness-novelty %: 0 (0)% -> 88.3 (0.7)% | Improved |
| graph-superposition representation (SuperHype) instead of bipartite representation | HYGENE · SBM, Ego, Tree (15 scenarios) | metrics won: 12 of 15 | Improved |
Closest papers by meaning
- HYGENE: A Diffusion-Based Hypergraph Generation Method (AAAI 2025 · similarity 0.89)
- Beyond Graphs: Can Large Language Models Comprehend Hypergraphs? (ICLR 2025 · similarity 0.86)
- Improved Expressivity of Hypergraph Neural Networks through High-Dimensional Generalized Weisfeiler-Leman Algorithms (ICML 2025 · similarity 0.86)
- Hypergraph Generation via Structured Stochastic Diffusion (NeurIPS 2026 · similarity 0.86)
- When Hypergraph Meets Heterophily: New Benchmark Datasets and Baseline (AAAI 2025 · similarity 0.86)
- SPHINX: Structural Prediction using Hypergraph Inference Network (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.
