Research map / Graph learning / GNN architectures
GREAD: Graph Neural Reaction-Diffusion Networks
Jeongwhan Choi, Seoyoung Hong, Noseong Park, Sung-Bae Cho
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 |
|---|---|---|---|
| Use the blurring-sharpening reaction-diffusion method | GREAD · 9 real-world datasets | average accuracy: GREAD-BS: 76.64; GGCN: 75.05 | Improved |
| Use soft adjacency instead of original adjacency (ablation) | GREAD-BS · Cornell | accuracy: 85.41 -> 86.49 | Improved |
| Use soft adjacency instead of original adjacency (ablation) | GREAD-BS · Film | accuracy: 36.68 -> 37.20 | Improved |
| Use learnable vector beta instead of scalar beta (ablation) | GREAD-BS · Texas | accuracy: 81.35 -> 88.92 | Improved |
| Use learnable vector beta instead of scalar beta (ablation) | GREAD-BS · Wisconsin | accuracy: 84.71 -> 89.41 | Improved |
| Add a reaction term to graph diffusion | GREAD · cSBM synthetic graph | Dirichlet energy | Improved |
| Use reaction-diffusion rather than diffusion-only processing | GREAD · Synthetic Cora across homophily rates | accuracy | Improved |
Closest papers by meaning
- A Generalized Neural Diffusion Framework on Graphs (AAAI 2024 · similarity 0.89)
- Diffusing to the Top: Boost Graph Neural Networks with Minimal Hyperparameter Tuning (ICLR 2025 · similarity 0.86)
- Feature Transportation Improves Graph Neural Networks (AAAI 2024 · similarity 0.86)
- Graph Neural PDE Solvers with Conservation and Similarity-Equivariance (ICML 2024 · similarity 0.85)
- When Graph Neural Networks Meet Dynamic Mode Decomposition (ICLR 2025 · similarity 0.84)
- Faster Local Solvers for Graph Diffusion Equations (NeurIPS 2024 · similarity 0.84)
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.
