Graph Transformers without Positional Encodings

Benchmark Model Rank Results
graph-classification-on-cifar10-100kEIGENFORMER–Accuracy (%): 70.194
graph-classification-on-mnistEIGENFORMER–Accuracy: 98.362
graph-classification-on-peptides-funcEIGENFORMER–AP: 0.6414
graph-regression-on-peptides-structEIGENFORMER–MAE: 0.2599
graph-regression-on-zincEIGENFORMER–MAE: 0.077
node-classification-on-clusterEIGENFORMER–Accuracy: 77.456
node-classification-on-patternEIGENFORMER–Accuracy: 86.738