Tengfei Ma

Thank you for your attention. The pooling method is different from SAGPool, as we expalined in our paper.

Assume we have 222 drugs, here are the shapes for each variable: adjs: a list with 4 elements, each adjs[i] with shape: (222, 222) features/x: (222, 582) y: (222, 222)...

It has been quite long since we finished this work, so I do not quite remember all the details. As to this question, I think we did not predict the...

The drug indication vectors are just multi-hot vectors. Each dimension is an indication. To see one example, you can refer to the SIDER database: http://sideeffects.embl.de/drugs/2756/

@Abhinav43 attentions = tf.concat(0, attention) is not concatenating with 0, but concatenating attention along the first dimension:) Sorry for my late reply due to travel. I will also address the...

i) I guess some of the errors are due to the version update of tensorflow. For example, tf.concat(0, attention) is the correct usage in previous version, but now I think...

@SudhirGhandikota You are right, the dimensions of the attention weights are equal to the number of nodes/drugs. And in fact the code "self.output_dim = placeholders['labels'].get_shape().as_list()[1]" did this:) Because in our...

> Is there a pytorch version available? @rojinsafavi Unfortunately we do not have a PyTorch version.

Hi, Due to data privacy we are not allowed to share the real datasets. As to the data format, you can refer to my another repo https://github.com/matenure/FastGCN/tree/master/data. That may give...