RAN-GNNs: breaking the capacity limits of graph neural networks
Open paper
Benchmark
Model
Rank
Results
graph-property-prediction-on-ogbg-molpcba
RandomGIN-vn+FLAG
–
Test AP: 0.2881 ± 0.0028
Ext. data: No
Validation AP: 0.3035 ± 0.0047
…
Rank counts only results with a code link.