Research map / Graph learning / GNN architectures
Equivariant Hypergraph Diffusion Neural Operators
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 ED-HNN instead of the strongest listed baseline | Node classification models · Cora | accuracy: 79.39 ± 1.36 -> 80.31 ± 1.35 | Helped |
| Use ED-HNN instead of the strongest listed baseline | Node classification models · Citeseer | accuracy: 73.08 ± 1.20 -> 73.70 ± 1.38 | Helped |
| Use ED-HNN instead of the strongest listed baseline | Node classification models · Pubmed | accuracy: 88.75 ± 0.33 -> 89.03 ± 0.53 | Helped |
| Use ED-HNN instead of the strongest listed baseline | Node classification models · Cora-CA | accuracy: 83.63 ± 1.47 -> 83.97 ± 1.55 | Helped |
| Use ED-HNN instead of the strongest listed baseline | Node classification models · DBLP-CA | accuracy: 91.69 ± 0.19 -> 91.90 ± 0.19 | Helped |
| Use ED-HNN instead of the strongest listed baseline | Node classification models · Congress | accuracy: 94.81 ± 0.81 -> 95.00 ± 0.99 | Helped |
| Use ED-HNN instead of the strongest listed baseline | Node classification models · Senate | accuracy: 51.83 ± 5.22 -> 64.79 ± 5.14 | Helped |
| Use ED-HNN instead of the strongest listed baseline | Node classification models · Walmart | accuracy: 65.46 ± 0.25 -> 66.91 ± 0.41 | Helped |
| Use ED-HNN instead of the strongest listed baseline | Node classification models · House | accuracy: 69.33 ± 2.20 -> 72.45 ± 2.28 | Helped |
| Add equivariant node-side message passing (ablation) | ED-HNN · Pubmed | accuracy: 89.03 ± 0.53 -> 89.56 ± 0.62 | Helped |
| Add equivariant node-side message passing (ablation) | ED-HNN · Walmart | accuracy: 66.91 ± 0.41 -> 67.24 ± 0.45 | Helped |
| Add equivariant node-side message passing (ablation) | ED-HNN · Cora | accuracy: 80.31 ± 1.35 -> 78.47 ± 1.62 | Hurt |
Closest papers by meaning
- Training-Free Message Passing for Learning on Hypergraphs (ICLR 2025 · similarity 0.90)
- Hypergraph Neural Architecture Search (AAAI 2024 · similarity 0.88)
- Deep Hypergraph Neural Networks with Tight Framelets (AAAI 2025 · similarity 0.88)
- When Hypergraph Meets Heterophily: New Benchmark Datasets and Baseline (AAAI 2025 · similarity 0.88)
- K-hop Hypergraph Neural Network: A Comprehensive Aggregation Approach (AAAI 2025 · similarity 0.88)
- LightHGNN: Distilling Hypergraph Neural Networks into MLPs for 100x Faster Inference (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.