Next Level Message-Passing with Hierarchical Support Graphs

Benchmark Model Rank Results
graph-regression-on-peptides-structGatedGCN-HSG#2MAE: 0.2421±0.0007
node-classification-on-pascalvoc-spGatedGCN-HSG#2macro F1: 0.4604±0.0059
graph-property-prediction-on-ogbg-molpcbaGatedGCN-HSG#4Test AP: 0.3129±0.0020
node-classification-on-coco-spGatedGCN-HSG#5macro F1: 0.3535±0.0032
graph-classification-on-peptides-funcGatedGCN-HSG#20AP: 0.6866±0.0038