AI Paper Atlas

Research map / Graph learning / GNN architectures

GREAD: Graph Neural Reaction-Diffusion Networks

Jeongwhan Choi, Seoyoung Hong, Noseong Park, Sung-Bae Cho

ICML 2023 · Graph learning › GNN architectures · approach: Simple and scalable GNNs · 4 citations (OpenAlex)

Read the paper

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 changedWhereMeasuredEffect
Use the blurring-sharpening reaction-diffusion methodGREAD · 9 real-world datasetsaverage accuracy: GREAD-BS: 76.64; GGCN: 75.05Improved
Use soft adjacency instead of original adjacency (ablation)GREAD-BS · Cornellaccuracy: 85.41 -> 86.49Improved
Use soft adjacency instead of original adjacency (ablation)GREAD-BS · Filmaccuracy: 36.68 -> 37.20Improved
Use learnable vector beta instead of scalar beta (ablation)GREAD-BS · Texasaccuracy: 81.35 -> 88.92Improved
Use learnable vector beta instead of scalar beta (ablation)GREAD-BS · Wisconsinaccuracy: 84.71 -> 89.41Improved
Add a reaction term to graph diffusionGREAD · cSBM synthetic graphDirichlet energyImproved
Use reaction-diffusion rather than diffusion-only processingGREAD · Synthetic Cora across homophily ratesaccuracyImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy