AllenWu18

Of course my email is [email protected]. But actually my question is that can you provide the original download link of these dataset, for I wanna to test more datasets in...

then is it should be KLD = -0.5 * torch.mean(torch.sum(1 + 2 * logvar - mu.pow(2) - logvar.exp().pow(2), 1)) or KLD = -0.5 / n_nodes * torch.sum(torch.sum(1 +2 * logvar...

Well, I think in the function normalize(mx) it normalizes the features by row, but if the node features are not one-hot form, and each node has its own feature like...

THX,I'll have a try