Hi everyone,
I am wondering if it is possible that the node attributes matrix (X) is 3-D instead of 2-D? For example: we want to use word embedding as the node attributes instead of bag of words representation. If using bag of words, X is [num of nodes, num of words in the vocab]. If using word embedding, X will be similar to sequence models input, which is [num of nodes, max sequence length, num of word embedding dimension].
And also, can we use GCN to perform node attributes prediction instead of node classification?
Hi everyone, I am wondering if it is possible that the node attributes matrix (X) is 3-D instead of 2-D? For example: we want to use word embedding as the node attributes instead of bag of words representation. If using bag of words, X is [num of nodes, num of words in the vocab]. If using word embedding, X will be similar to sequence models input, which is [num of nodes, max sequence length, num of word embedding dimension].
And also, can we use GCN to perform node attributes prediction instead of node classification?
Thanks!