Research map / Graph learning / Graph self-supervised learning
HyperPLR: Hypergraph Generation through Projection, Learning, and Reconstruction
Weihuang Wen, Tianshu Yu
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes HyperPLR, a hypergraph generation method built on projection, learning, and reconstruction, aimed at producing realistic higher-order collaboration networks.
Problem
Generating realistic hypergraphs that capture group (polyadic) interactions in collaboration networks, for use in promoting and validating hypergraph methods.
Approach
Generates hypergraphs by projecting them to a lower-order representation, learning a model on the projection, and reconstructing the hyperedges; details beyond the abstract are not available.
Closest papers by meaning
- HYGENE: A Diffusion-Based Hypergraph Generation Method (AAAI 2025 · similarity 0.90)
- SPHINX: Structural Prediction using Hypergraph Inference Network (ICML 2025 · similarity 0.88)
- HypeBoy: Generative Self-Supervised Representation Learning on Hypergraphs (ICLR 2024 · similarity 0.88)
- Hypergraph Generation via Structured Stochastic Diffusion (NeurIPS 2026 · similarity 0.87)
- When Hypergraph Meets Heterophily: New Benchmark Datasets and Baseline (AAAI 2025 · similarity 0.87)
- HiGen: Hierarchical Graph Generative Networks (ICLR 2024 · 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.
