This source code archive accompanies the An end-to-end attention-based approach for learning on graphs paper, out now in Nature Communications. It includes the code required to run experiments ...
$ python train_source.py --logdir outputs $ python main.py --logdir outputs --trained outputs/best_model.pt --slope 0.2 For training on Office dataset using ResNet-50 $ python ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback