pygcn
pygcn copied to clipboard
tkipf
Graph Convolutional Networks in PyTorch
Hi @tkipf . I have some confusion about residual connection in GCN. ``` def forward(self, x, adj): # x size: [2708, 1433] # adj size: [2708, 2708] x = F.relu(self.gc1(x,...
Hello,tkipf ! Thanks for your share! In the trainng process,features are 2708 dims, does it involve test samples? thank you very much!
Freeze model performance in multiple training process. The simplest way is to freeze one-hot encoding for each class every time we re-run the train.py. By applying this, we can freeze...
Early Stop scheme could enhance the performance to a certain extent. Why it's not used in this codes?
I noticed that SpecialSpmmFunction is the subclass of torch.autograd.Function and there is only one object in class SpGraphAttentionLayer. `class SpGraphAttentionLayer(nn.Module): def __init__(self, in_features, out_features, dropout, alpha, concat=True): super(SpGraphAttentionLayer, self).__init__() self.in_features...
Hi, Thank you for providing such a great model. I would like to ask , can we apply Multiple Instance learning on text-GCN ? and which level that would be...
In the cora.content file, I don't know what is the features mean.
Thank you for sharing the work. Is the model for detecting communities? (classifying nodes with community labels?) Please include the intended output in the Readme. Then it will be easier...
I notice the standard deviation for initialization used output size instead of input size. Is this implementation intended? `self.weight = Parameter(torch.FloatTensor(in_features, out_features))` `stdv = 1. / math.sqrt(self.weight.size(1))`
Hi! How do you process the data and save it as .content format ? what is the the content of 'cora.cities' and 'cora.content' ? Thanks!
