# How should I deal with multi-dimensional tensors for nodes in a graph convolution network?

How to work with GCN when the features of each node is not a 1D vector? For example, if the graph has N nodes and each node has features of the form $$C \times D \times E$$.

Also, is there an open-source implementation for such a case?

• Hi and welcome to AI SE! Have you tried to reshape your tensor into a 1D vector of shape $C*D*E$? – nbro Apr 7 at 13:17