Convolutional Networks on Graphs for Learning Molecular Fingerprints

Benchmark Model Rank Results
drug-discovery-on-hiv-datasetGraphConv#2AUC: 0.822
drug-discovery-on-muvGraphConv#3AUC: 0.836
drug-discovery-on-tox21GraphConv#5AUC: 0.846
drug-discovery-on-toxcastGraphConv#3AUC: 0.754
graph-regression-on-lipophilicityGC#11RMSE: 0.655
node-classification-on-citeseer-05GCN-FP#12Accuracy: 43.9%
node-classification-on-citeseer-1GCN-FP#12Accuracy: 54.3%
node-classification-on-citeseer-with-publicGCN-FP#39Accuracy: 61.5%
node-classification-on-cora-05GCN-FP#11Accuracy: 50.5%
node-classification-on-cora-1GCN-FP#12Accuracy: 59.6%
node-classification-on-cora-3GCN-FP#12Accuracy: 71.7%
node-classification-on-cora-with-public-splitGCN-FP#35Accuracy: 74.6%
node-classification-on-pubmed-003GCN-FP#10Accuracy: 56.2%
node-classification-on-pubmed-005GCN-FP#11Accuracy: 63.2%
node-classification-on-pubmed-01GCN-FP#11Accuracy: 70.3%
node-classification-on-pubmed-with-publicGCN-FP#30Accuracy: 76.0%