Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting

Benchmark Model Rank Results
graph-regression-on-zinc-100kGSN#2MAE: 0.115
graph-property-prediction-on-ogbg-molhivdirectional GSN#14Test ROC-AUC: 0.8039 ± 0.0090Ext. data: No…
graph-property-prediction-on-ogbg-molhivGSN#26Test ROC-AUC: 0.7799 ± 0.0100Ext. data: No…
graph-regression-on-zinc-500kGSN#22MAE: 0.101