Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/PretrainGNN

PretrainGNN

Reported on 22 benchmarks across 2 tasks · 1 paper · 4 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology11 results

Molecular Property PredictiononToxCast
ROC-AUC· 2019-05-29
65.7
best: 78.2 (DumplingGNN)
SOTA
Strategies for Pre-training Graph Neural Networks arXiv:1905.12265
Molecular Property PredictiononBACE
ROC-AUC· 2019-05-29
84.5
best: 88.4 (MolXPT)
SOTA
Strategies for Pre-training Graph Neural Networks arXiv:1905.12265
Molecular Property PredictiononFreeSolv
RMSE· 2019-05-29
2.764
best: 1.09 (SMA)
Strategies for Pre-training Graph Neural Networks arXiv:1905.12265
Molecular Property Predictiononclintox
ROC-AUC· 2019-05-29
72.6
best: 99.2 (Deep-CBN)
Strategies for Pre-training Graph Neural Networks arXiv:1905.12265
Molecular Property PredictiononLipophilicity
RMSE· uses extra data· 2019-05-29
0.739
best: 0.603 (Uni-Mol)
Strategies for Pre-training Graph Neural Networks arXiv:1905.12265
Molecular Property PredictiononQM7
MAE· 2019-05-29
113.2
best: 41.8 (Uni-Mol)
Strategies for Pre-training Graph Neural Networks arXiv:1905.12265
Molecular Property PredictiononBBBP
ROC-AUC· 2019-05-29
68.7
best: 96.4 (DumplingGNN)
Strategies for Pre-training Graph Neural Networks arXiv:1905.12265
Molecular Property PredictiononQM9
MAE· 2019-05-29
0.00922
best: 0.00467 (Uni-Mol)
Strategies for Pre-training Graph Neural Networks arXiv:1905.12265
Molecular Property PredictiononQM8
MAE· 2019-05-29
0.02
best: 0.0156 (Uni-Mol)
Strategies for Pre-training Graph Neural Networks arXiv:1905.12265
Molecular Property PredictiononSIDER
ROC-AUC· 2019-05-29
62.7
best: 91.11 (BioAct-Het)
Strategies for Pre-training Graph Neural Networks arXiv:1905.12265
Molecular Property PredictiononTox21
ROC-AUC· 2019-05-29
78.1
best: 92.4 (Deep-CBN)
Strategies for Pre-training Graph Neural Networks arXiv:1905.12265

Medical11 results

Atomistic DescriptiononToxCast
ROC-AUC· 2019-05-29
65.7
best: 78.2 (DumplingGNN)
SOTA
Strategies for Pre-training Graph Neural Networks arXiv:1905.12265
Atomistic DescriptiononBACE
ROC-AUC· 2019-05-29
84.5
best: 88.4 (MolXPT)
SOTA
Strategies for Pre-training Graph Neural Networks arXiv:1905.12265
Atomistic DescriptiononFreeSolv
RMSE· 2019-05-29
2.764
best: 1.09 (SMA)
Strategies for Pre-training Graph Neural Networks arXiv:1905.12265
Atomistic Descriptiononclintox
ROC-AUC· 2019-05-29
72.6
best: 99.2 (Deep-CBN)
Strategies for Pre-training Graph Neural Networks arXiv:1905.12265
Atomistic DescriptiononLipophilicity
RMSE· uses extra data· 2019-05-29
0.739
best: 0.603 (Uni-Mol)
Strategies for Pre-training Graph Neural Networks arXiv:1905.12265
Atomistic DescriptiononQM7
MAE· 2019-05-29
113.2
best: 41.8 (Uni-Mol)
Strategies for Pre-training Graph Neural Networks arXiv:1905.12265
Atomistic DescriptiononBBBP
ROC-AUC· 2019-05-29
68.7
best: 96.4 (DumplingGNN)
Strategies for Pre-training Graph Neural Networks arXiv:1905.12265
Atomistic DescriptiononQM9
MAE· 2019-05-29
0.00922
best: 0.00467 (Uni-Mol)
Strategies for Pre-training Graph Neural Networks arXiv:1905.12265
Atomistic DescriptiononQM8
MAE· 2019-05-29
0.02
best: 0.0156 (Uni-Mol)
Strategies for Pre-training Graph Neural Networks arXiv:1905.12265
Atomistic DescriptiononSIDER
ROC-AUC· 2019-05-29
62.7
best: 91.11 (BioAct-Het)
Strategies for Pre-training Graph Neural Networks arXiv:1905.12265
Atomistic DescriptiononTox21
ROC-AUC· 2019-05-29
78.1
best: 92.4 (Deep-CBN)
Strategies for Pre-training Graph Neural Networks arXiv:1905.12265