can you release PyTorch edition? about gcdn HOT 5 OPEN

Hi, unfortunately we do not have a Pytorch implementation at the moment.

from gcdn.

Could you talk about the difference between your graph convolution and the counterpart in paper《Semi-supervised classification with graph convolutional networks》.
Sorry, I'm not clear about GCN, but I am interested in this structure.

from gcdn.

I want to know that this code is for your ICIP paper or your journal paper ?

from gcdn.

The code is from the journal version. You can find all the details on the graph convolution on https://arxiv.org/abs/1907.08448. The main difference of the graph convolution that we use with respect to the GCN by Kipf et al. is that it is computes the aggregation weights in an adaptive way, i.e. as a function of differences of feature vectors, and this function is implemented with a small neural network.

from gcdn.

thank you very much.

from gcdn.