AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Molecular Representation Learning via Heterogeneous Motif Graph Neural Networks

Zhaoning Yu, Hongyang Gao

ICML 2022 · Graph learning › Graph self-supervised learning · approach: Molecular graph pretraining · 13 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
Add heterogeneous motif-level representations to atom-level GIN (ablation)HM-GNN · PTC, MUTAG, PROTEINSaccuracy: 64.6 $\pm$ 7.0 -> 78.8 $\pm$ 6.5; 89.4 $\pm$ 5.6 -> 96.3 $\pm$ 2.6; 76.2 $\pm$ 2.8 -> 79.9 $\pm$ 3.1Improved
Add motif-motif interactions to the heterogeneous motif graph (ablation)HM-GNN · PTC, MUTAG, PROTEINaccuracy: 76.4$\pm$4.4 -> 78.8$\pm$6.5; 94.6$\pm$4.3 -> 96.3$\pm$2.6; 78.3$\pm$3.5 -> 79.9$\pm$3.1Improved
Combine PTC with PTC_MM and shared motif vocabulary (ablation)HM-GNN multi-task learning · PTC, 90% trainingaccuracy: 71.8 $\pm$ 4.1 -> 76.5 $\pm$ 3.3Improved
Combine PTC with PTC_MM and shared motif vocabulary (ablation)HM-GNN multi-task learning · PTC, 50% trainingaccuracy: 65.1 $\pm$ 0.8 -> 69.2 $\pm$ 0.8Improved
Combine PTC with PTC_MM and shared motif vocabulary (ablation)HM-GNN multi-task learning · PTC, 10% trainingaccuracy: 59.9 $\pm$ 1.9 -> 66.7 $\pm$ 1.9Improved
Combine PTC with PTC_FR and shared motif vocabulary (ablation)HM-GNN multi-task learning · PTC, 90% trainingaccuracy: 71.8 $\pm$ 4.1 -> 84.3 $\pm$ 3.8Improved
Combine PTC with PTC_FR and shared motif vocabulary (ablation)HM-GNN multi-task learning · PTC, 50% trainingaccuracy: 65.1 $\pm$ 0.8 -> 77.3 $\pm$ 0.8Improved
Combine PTC with PTC_FR and shared motif vocabulary (ablation)HM-GNN multi-task learning · PTC, 10% trainingaccuracy: 59.9 $\pm$ 1.9 -> 74.0 $\pm$ 1.7Improved
Use HM-GNN instead of the strongest listed baselineTUDataset graph classification · PTC, MUTAG, NCI1, PROTEINS, MUTAGENICITYaccuracyImproved
Use HM-GNN rather than PNAogbg-molhiv · ogbg-molhivROC-AUC: 79.05 $\pm$ 1.32 -> 79.03 $\pm$ 0.92No clear effect
Add PNA to HM-GNNHM-GNN · ogbg-molhivROC-AUC: 79.03 $\pm$ 0.92 -> 80.20 $\pm$ 1.18Improved
Increase the motif vocabulary keeping ratio beyond 80% (ablation)HM-GNN · ogbg-molhivROC-AUCHurt

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