Xujiang Zhao

I think it is the author using the technical "MC dropout" to do the Bayesian inference, which means the if we add dropout after each convolutional layer, then the CNN...

So you don't have the physical feature for each node, right? Then we can use the identity matrix as the spatial feature for input (line 49 in "GCN_GRU_run.py")

I update the code now :)

> When I try to run demo, some errors occur. > For example, GRU_cell.py does not have GRUCell_ori. > Are there any complete file? Hi, Sorry for the late reply...

> Yes. I used different hyperparams, as described in the paper: > > * 'dataset' : 'nell.0.001', > * 'model' : 'gcn', > * 'learning_rate' : 0.01, > * 'epochs'...