pygcn
pygcn copied to clipboard
question about inputs matrix X, the node feature matirx
I want to know how I can get the feature matrix of nodes with my own training data, suppose that the number of nodes is N and the dim of every featue vector is d, how can I get the inputs X whose shape is N*d? Thanks a lot!
If you have Node N and every node has dim of d then your feature matrix will be N*D already. if you don't have feature matrix, you can use identity matrix or featureless gcn model.
the feature vector marked attribute of the node,you can create the feature vector by judging the Node using some metircs,it should come with data rather than the model or code writer
if your node represent a person,maybe those features are age,gender,height etc. Those features can describe your subjects.