dbusbridge / gcn_tutorial Goto Github PK

Hi, I just found your repository and and it's really helpful to understand graph network.
I just gone through your code files and it was really informative and maintained.
In your experiments you have only predicted node and presented node classification problem.
I have few doubts, can we use same network for edge classification or do we have other powerful networks for edge classification instead of node classification?
If you can post a notebook or python code with edge classification that would be very helpful though.

Thank you,
And keep posting and learning. :)

I ran 01_karate_unsupervised.py with env_graph_convnet, the following error appeared.

Traceback (most recent call last):
File "01_karate_unsupervised.py", line 40, in
'adj_norm': tf.sparse_placeholder(tf.float32, name="adj_mat"),
AttributeError: module 'tensorflow' has no attribute 'sparse_placeholder'

Does anyone know what are the causes and solutions?

It seems here it should be self.b, not self.bias.