AI Paper Atlas

Research map / Graph learning / GNN architectures

GRAND: Graph Neural Diffusion

Ben Chamberlain, James Rowbottom, Maria I Gorinova, Michael Bronstein, Stefan Webb, Emanuele Rossi

ICML 2021 · Graph learning › GNN architectures · approach: GNN generalization theory · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

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 GRAND-l instead of GDECora, Planetoid splits · Cora, Planetoid splitstest accuracy: 83.8 \pm 0.5 -> 84.7 \pm 0.6Improved
Use GRAND-nl-rw instead of GDECiteSeer, Planetoid splits · CiteSeer, Planetoid splitstest accuracy: 72.5 \pm 0.5 -> 73.6 \pm 0.3Improved
Use GRAND-nl-rw instead of CGNNPubMed, Planetoid splits · PubMed, Planetoid splitstest accuracy: 80.2 \pm 0.3 -> 81.0 \pm 0.4Improved
Use GRAND-l instead of GATCora, random splits · Cora, random splitstest accuracy: 81.8 \pm 1.3 -> 83.6 \pm 1.0Improved
Use GRAND-nl-rw instead of GCNCiteSeer, random splits · CiteSeer, random splitstest accuracy: 71.9 \pm 1.9 -> 74.1 \pm 1.7Improved
Use GRAND-l instead of GATPubMed, random splits · PubMed, random splitstest accuracy: 78.7 \pm 2.3 -> 78.8 \pm 1.7No clear effect
Use GRAND-l instead of CGNNCoauthor CS, random splits · Coauthor CS, random splitstest accuracy: 92.3 \pm 0.2 -> 92.9 \pm 0.4Improved
Use GRAND-nl-rw instead of GAT-pprComputer, random splits · Computer, random splitstest accuracy: 85.4 \pm 0.3 -> 85.8 \pm 1.5No clear effect
Use GRAND-nl-rw instead of GDEPhoto, random splits · Photo, random splitstest accuracy: 92.4 \pm 2.0 -> 92.5 \pm 1.0No clear effect
Use GRAND-nl-rw instead of GATogb-arxiv, random splits · ogb-arxiv, random splitstest accuracy: 73.65 \pm 0.11 -> 72.23 \pm 0.20Hurt
Use scaled dot product attention rather than Bahdanau attention (ablation)GRAND · Node classification benchmarkstest accuracyImproved
Increase adaptive solver tolerances relative to defaults (ablation)GRAND with adaptive step-size ODE solvers · Node classification benchmarksprediction accuracyImproved

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