Research map / Probabilistic and scientific modeling / Molecules and proteins
ReLaSH: Reconstructing Joint Latent Spaces for Efficient Generation of Synthetic Hypergraphs with Hyperlink Attributes
Feiyan Ma, Shihao Wu, Gongjun Xu, Ji Zhu
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 |
|---|---|---|---|
| add degree-sequence calibration (ReLaSHc) at generation (ablation) | ReLaSH-(7, 0, 2) · MIMIC-III patient profiles | FED: FED 0.532 -> 0.013; Delta Hv 3.260 -> 27.794 | Mixed |
| add degree-sequence calibration (ReLaSHc) at generation (ablation) | ReLaSH-(2, 2, 2) · MADStat co-citation | FED: FED 1.246 -> 5.481; Delta Hv 1.996 -> 3.890 | Hurt |
| add degree-sequence calibration (ReLaSHc) at generation (ablation) | ReLaSH-(2, 7, 8) · MADStat co-citation | FED: FED 1.060 -> 0.947; Delta Hv 1.914 -> 2.772 | Mixed |
| add degree-sequence calibration (ReLaSHc) at generation (ablation) | ReLaSH-(5, 0, 6) · Recipe generation | FED: FED 0.003 -> 0.191; Delta Hv 2.129 -> 3.583 | Hurt |
| add degree-sequence calibration (ReLaSHc) at generation (ablation) | ReLaSH-(5, 0, 16) · Recipe generation | FED: FED 0.766 -> 0.180; Delta Hv 2.355 -> 1.847 | Mixed |
| increase hyperlink-only latent dimension k3 from 2 to 16 (ablation) | ReLaSH-(7, 0, k3) · MIMIC-III patient profiles | FED: FED 0.532 -> 11.738 | Hurt |
| increase hyperlink-only latent dimension k3 from 2 to 6 (ablation) | ReLaSH-(5, 0, k3) · Recipe generation | FED: FED 0.293 -> 0.003 | Improved |
| increase hyperlink-only latent dimension k3 from 6 to 16 (ablation) | ReLaSH-(5, 0, k3) · Recipe generation | FED: FED 0.003 -> 0.766 | Hurt |
| increase latent dimension k from 6 to 12 (ablation) | joint embedding model (simulation) · simulated hypergraphs, rho=0 | slope of log error vs log n: -0.4907 -> -0.5462 | No clear effect |
Closest papers by meaning
- HyperPLR: Hypergraph Generation through Projection, Learning, and Reconstruction (ICLR 2025 · similarity 0.88)
- Hypergraph Representation Learning with Hyperlink Random Effects (NeurIPS 2026 · similarity 0.88)
- SPHINX: Structural Prediction using Hypergraph Inference Network (ICML 2025 · similarity 0.87)
- HYGENE: A Diffusion-Based Hypergraph Generation Method (AAAI 2025 · similarity 0.87)
- GLAD: Improving Latent Graph Generative Modeling with Simple Quantization (AAAI 2025 · similarity 0.86)
- HypeBoy: Generative Self-Supervised Representation Learning on Hypergraphs (ICLR 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.
