skx300
skx300
Isn't **loopback** controlling it?
If it is biparty network, that's yes. If it is not, you could have something like A-A-B or something else.
Thank you. I understand that. But should sample the A[10, :] * T[:4], right? The T is in shape (number of nodes) x (number of node types). The column of...
@preetham-salehundam I haven't figured out that. Have you got any idea? I think it is necessary to feed the concatenated vector into one dense layer, no matter whether they have...
I think I may get the point. The dense layer (which is a matrix weight W^k), multiplied by the concatenated vector of node's itself and its neighbors, can be split...
I think for unsupervised learning, we only need to split edges to training and validation sets.
As far as I know, the link_pred_layer.loss is for unsupervised learning. The name of itself also tells that the unsupervised learning is converted to a kind of link prediction task....
From the literature of graph embedding , they are equivalent.