Reference implementation of the certificates proposed in the paper:
"Graph neural networks to learn joint representations of disjoint molecular graph"
Chen Shao, Chen Zhou, and Pascal Friederich
The notebook demo.ipynb shows an example of how to use our dataset for a pretrained GCN model.
You can use scripts/train_and_acc.py to train a model from scratch on a cluster.
Please cite our paper if you use this code or dataset in your own work:
@inproceedings{TODO,
title = { Graph neural networks to learn joint representations of disjoint molecular graphs},
author = {Chen Shao, Chen Zhou, and Pascal Friederich},
}