yifan-h / cs-gnn Goto Github PK

Nice to meet you, I am interesting in your paper in 2020ICLR-"MEASURING AND IMPROVING THE USE OF GRAPH INFORMATION IN GRAPH NEURAL NETWORKS".But when I plan to caculate some feature smoothness,I found it has some difference.I wish you could help me out!
To caculate the feature smoothness of dataset --cora, I use the folloing codes:

result=np.zeros(features.shape[1])
for i in range(features.shape[0]):
    z=np.zeros((1,features.shape[1]))
    for j in range(features.shape[0]):
        if adj[i,j]==1 and i!=j:
            z+=features[i].toarray()-features[j].toarray()
    zz=np.squeeze(z)
    result+=zz*zz

result=np.sum(result)/(features.shape[1]*5429)
print(result)

But the result of my codes is so big.I'm little confused !
THANKS A LOT!

I find that when computing feature smoothness, the code uses the function feature_broadcast (I find it's to merge feature of a node with its neighbors).

    for i in range(times):
        feats = feature_broadcast(feats, G_org)

I find the formula in paper just used original feats with normalization. So I wonder why we need to calculate this feature broadcast?
The similar problem is on label_broadcast, which I think it's to remove some edges randomly. Why we need to do that?

Thanks for sharing the code! @yifan-h

Do you have some experimental results comparing CS-GNN vs GAT on PPI?

Hi. yifan, sorry to disturb you again. There is a error AttributeError: 'Graph' object has no attribute 'selfloop_edges' in utils.py: G.remove_edges_from(G.selfloop_edges()), How can i to solve it? Thanks.

In my recent learning, I'm unsure how to caculate $\lambda_l$. In other words, Do you use test dataset nodes in your calculations of label smoothness? If the situation in the traing set is: The two vertices of an edge belong to the training set and the test set respectively. Then this edge will be ignored automaticly?

Hi. Yifan, when I run the code, there is a error:AttributeError: 'Graph' object has no attribute 'node' in such file: utils.py line 23: if not 'val' in G.node[node] or not 'test' in G.node[node]:, would you please tell me how to solve it? Thanks.