Hi, could you release the code of GRAND_DropEdge?
I tried the code of Dropedge, but the result isn't satisfied.
`def rand_prop_dropedge(adj_dropedge, features, training):
if training:
nnz = adj_dropedge.nnz
perm = np.random.permutation(nnz)
preserve_nnz = int(nnz * 0.5)
perm = perm[:preserve_nnz]
r_adj = sp.coo_matrix((adj_dropedge.data[perm],
(adj_dropedge.row[perm],
adj_dropedge.col[perm])),
shape=adj_dropedge.shape)
Hi, could you release the code of GRAND_DropEdge? I tried the code of Dropedge, but the result isn't satisfied. `def rand_prop_dropedge(adj_dropedge, features, training): if training: nnz = adj_dropedge.nnz perm = np.random.permutation(nnz) preserve_nnz = int(nnz * 0.5) perm = perm[:preserve_nnz] r_adj = sp.coo_matrix((adj_dropedge.data[perm], (adj_dropedge.row[perm], adj_dropedge.col[perm])), shape=adj_dropedge.shape)
where
adj_dropedge
is fromadj = nx.adjacency_matrix(nx.from_dict_of_lists(graph)) adj = adj + adj.T.multiply(adj.T > adj) - adj.multiply(adj.T > adj) adj_dropedge = adj adj_dropedge = sp.coo_matrix(adj_dropedge)
Thanks!