Research map / Graph learning / Graph self-supervised learning
Nonlinear Feature Diffusion on Hypergraphs
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 |
|---|---|---|---|
| Nonlinear feature+label diffusion (HyperND) used as embedding for a linear classifier, versus APPNP baseline | HyperND · Citeseer, Cora-author, Cora-cit, DBLP, Pubmed | accuracy (%): e.g. +8.6 on Citeseer, +6.0 on Cora-author, +1.1 on Cora-cit, +0.7 on DBLP, +1.3 on Pubmed | Helped |
| Nonlinear feature+label diffusion (HyperND) versus APPNP on the foodweb hypergraph (no features) | HyperND · Foodweb | accuracy (%): -5.03 vs APPNP | Hurt |
| Using the diffusion embedding of HyperND with graph-convolution features vs. adding HyperGCN final embedding as extra features (ablation) | HyperND embedding + HyperGCN embedding (E4) · DBLP, Pubmed, Cora-author, Cora-cit, Citeseer | accuracy | No clear effect |
| Label-only nonlinear diffusion (E1, U=Y) versus diffusion including features (E3) (ablation) | HyperND · DBLP, Pubmed, Cora-author, Cora-cit, Citeseer | accuracy | Hurt |
Closest papers by meaning
- Hypergraph-enhanced Dual Semi-supervised Graph Classification (ICML 2024 · similarity 0.90)
- Fast Algorithms for Hypergraph PageRank with Applications to Semi-Supervised Learning (ICML 2024 · similarity 0.89)
- Hypergraph Label Propagation Network (AAAI 2020 · similarity 0.89)
- HyperGCN: A New Method For Training Graph Convolutional Networks on Hypergraphs (NeurIPS 2019 · similarity 0.89)
- Training-Free Message Passing for Learning on Hypergraphs (ICLR 2025 · similarity 0.88)
- Diffusing to the Top: Boost Graph Neural Networks with Minimal Hyperparameter Tuning (ICLR 2025 · 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.