Yfhu

data split issue

2

Hello, thanks for sharing your work. In your implementation, I noticed that you split the dataset as "train:range(140), val:range(200, 500), test:range(500, 1500)", I want to know why you split dataset...

What is the difference between two adjacency matrix normalization?

5

Hello, thanks for the amazing work. In your implementation, you use D^-1*A, but I noticed that some other work use D^-1/2*A*D^-1/2, I suppose these two calculation won't get the same...

torch_geometric?

1

Hello, thanks for the amazing work, I see you import torch_geometric, so is this code based on rusty1s' pytorch_geometric?

Hello, thanks for sharing your work. In your implementation, I noticed that you split the dataset as "train:range(140), val:range(200, 500), test:range(500, 1500)", I want to know why you split dataset...

Some questions about the paper

1

Hello, thanks for releasing your code. I think you adopt the same pooling method as SAGPool to select nodes to be perserved in a graph, but in figure3, The nodes...