AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Simple GNN Regularisation for 3D Molecular Property Prediction and Beyond

Jonathan Godwin, Michael Schaarschmidt, Alexander L Gaunt, Alvaro Sanchez-Gonzalez, Yulia Rubanova, Petar Veličković, James Kirkpatrick, Peter Battaglia

ICLR 2022 · Graph learning › Graph self-supervised learning · approach: Molecular graph pretraining · 8 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 Noisy Nodes to GNSGNS · OC20 IS2RE test OOD BotheV MAE: 0.638 -> 0.465Improved
Add Noisy Nodes to GNSGNS · OC20 IS2RS test OOD BothADwT: 46.9% -> 52.7%Improved
Add Noisy Nodes to GNSGNS · QM9 teststd. MAE: 1.17 -> 0.90Improved
Add noise but omit the node-level correction target (ablation)GNS · QM9 teststd. MAE: 1.17 -> 1.16No clear effect
Use the invariance variant (ablation)GNS-10 + Noisy Nodes · QM9 teststd. MAE: 0.88 -> 0.92Hurt
Increase depth from 10 to 30 layers (ablation)GNS-10 + Noisy Nodes · QM9 teststd. MAE: 0.89 -> 0.88Improved
Interpolate between initial and final positions rather than sample trajectory states (ablation)GNS + Noisy Nodes · OC20 IS2RE ID validationeV MAE: 0.47 -> 0.45Improved
Add Noisy Nodes to 50-layer MPNNMPNN + Virtual Node · OGBG-PCQM4MMAE: 0.1236 -> 0.1218Improved
Add Noisy Nodes to 16-layer MPNNMPNN + Virtual Node · OGBG-MOLPCBAMean AP: 27.6% ± 0.004 -> 28.1% ± 0.002Improved
Add Noisy Nodes to 4-layer GCN with residual connections4-layer GCN · OGBN-Arxivaccuracy: 72.39% ± 0.002 -> 72.52% ± 0.003Improved
Set category-flip probability to 0.1 instead of 0.05 (ablation)8-layer MPNN + Virtual Node + Noisy Nodes · OGBG-MOLPCBAMean AP: 28.1% +- 0.001 -> 28.0% +- 0.003Hurt
Use DropEdge instead of Noisy Nodes (ablation)MPNN · OGBG-MOLPCBAMean AP: 27.4% ± 0.002 -> 27.5% ± 0.001No clear effect

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