GraphConv

Reported on 5 benchmarks across 1 task · 1 paper · 5 SOTA

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

Medical5 results

Drug DiscoveryonTox21
AUC· 2015-09-30
0.846
best: 0.961 (elEmBERT-V1)
SOTA
Convolutional Networks on Graphs for Learning Molecular Fingerprints arXiv:1509.09292
Drug DiscoveryonHIV dataset
AUC· 2015-09-30
0.822
best: 0.851 (GraphConv + dummy super node + focal loss)
SOTA
Convolutional Networks on Graphs for Learning Molecular Fingerprints arXiv:1509.09292
Drug DiscoveryonToxCast
AUC· 2015-09-30
0.754
best: 0.777 (TrimNet)
SOTA
Convolutional Networks on Graphs for Learning Molecular Fingerprints arXiv:1509.09292
Drug DiscoveryonMUV
AUC· 2015-09-30
0.836
best: 0.851 (TrimNet)
SOTA
Convolutional Networks on Graphs for Learning Molecular Fingerprints arXiv:1509.09292
Drug DiscoveryonPCBA
AUC· 2015-09-30
0.855
best: 0.867 (GraphConv + dummy super node)
SOTA
Convolutional Networks on Graphs for Learning Molecular Fingerprints arXiv:1509.09292