AI Paper Atlas

Research map / Graph learning / GNN architectures

Rethinking Graph Transformers with Spectral Attention

Devin Kreuzer, Dominique Beaini, William L. Hamilton, Vincent Létourneau, Prudencio Tossou

NeurIPS 2021 · Graph learning › GNN architectures · approach: GNN generalization theory · 70 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
add node-wise learned positional encoding (LPE) to sparse and full attention (ablation)SAN · ZINC and MolHIVMAE / ROC-AUCImproved
add node-wise LPE (ablation)SAN · PATTERN and CLUSTERaccuracyImproved
use full attention instead of sparse attention (gamma > 0) (ablation)SAN · PATTERN and CLUSTERaccuracyImproved
use full attention instead of sparse attention (ablation)SAN · ZINC and MolHIVMAE / ROC-AUCMixed
SAN vs MolHIV state of the art (PNA, DGN) on test setSAN · MolHIV testROC-AUCHurt
SAN vs PNA and DGN on validation setSAN · MolHIV validationROC-AUC (%): 85.30 vs 84.25 (PNA), 84.70 (DGN)Improved
SAN vs other attention-based models and GT (full)SAN · ZINC, PATTERN, CLUSTER, MolHIVbenchmark metricsImproved

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