Kronecker approximations for GNNs

The Kronecker approximation depends on a NN architecture. We should support important GNN layers such as the [`GCNConv` layer](https://pytorch-geometric.readthedocs.io/en/latest/modules/nn.html#convolutional-layers). A reference Kronecker approximation for the GCNConv can be found at [here](https://github.com/russellizadi/ssp/blob/master/experiments/psgd.py). @runame proposed and implemented Kronecker approximations for another GNN layer.