Higher Powers Implementation

[datavistics]

MixHop-and-N-GCN/src/layers.py

Lines 54 to 56 in 6e4ae00

	for iteration in range(self.iterations-1):
	base_features = spmm(normalized_adjacency_matrix["indices"], normalized_adjacency_matrix["values"], base_features.shape[0], base_features)
	return base_features

To me it looks like this is implementing
H(l+1) = σ(A^j * H(l) * W(l))

Can you explain where W_j and the concatenation are taking place?

[benedekrozemberczki]

In the respective setup_layer_structures method in the trainer_and_networks.py file.