AI Paper Atlas

Research map / Graph learning / GNN architectures

Directional Message Passing on Molecular Graphs via Synthetic Coordinates

Johannes Gasteiger, Chandan Yeshwanth, Stephan Günnemann

NeurIPS 2021 · Graph learning › GNN architectures · approach: Equivariant networks for molecules · 12 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 PPR graph distance features (ablation)DeeperGCN · ZINCMAE: 0.317 -> 0.227Improved
add RDKit distance bounds features (ablation)DeeperGCN · ZINCMAE: 0.317 -> 0.264Improved
add line graph on top of distance (ablation)DeeperGCN (Bounds+PPR) · ZINCMAE: 0.228 -> 0.178Improved
add angle features on top of distance and line graph (ablation)DeeperGCN (Bounds+PPR) · ZINCMAE: 0.178 -> 0.142Improved
line graph and angles added to SMP with PPR (ablation)SMP · ZINCMAE: 0.151 -> 0.153No clear effect
combine bounds and PPR rather than bounds alone (ablation)SMP full directional · ZINCMAE: 0.113 -> 0.109Improved
use synthetic bounds/PPR coordinates instead of MMFF94/ETKDG conformers (ablation)DeeperGCN · ZINCMAE: 0.274 -> 0.142 (ETKDG vs Bounds+PPR)Improved
add synthetic distances and angles (ablation)DimeNet++ · coordinate-free QM9 U0MAE (meV): 41.9 -> 28.7Improved
add angles on top of distances (ablation)DimeNet++ · coordinate-free QM9 U0MAE (meV): 32.1 -> 28.7Improved
convert DeeperGCN to line graph (directional MPNN) (ablation)DeeperGCN · QM9 U0MAE (meV): 114 -> 233 (bounds)Hurt
convert DeeperGCN to line graph (directional MPNN) (ablation)DeeperGCN · ogbg-molhivROC-AUC: 0.734 -> 0.697 (PPR)Hurt
add PPR distance without line graph (ablation)DeeperGCN · QM9 U0 / ogbg-molhivMAE / ROC-AUC: 106 -> 88; 0.728 -> 0.734Improved

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