Hello, the paper said: "an explicit (stochastic) corruption function (\tilde{X}, \tilde{A}) = C(X, A)."
However, in the code, I only find the corruption on node attributes:
idx = np.random.permutation(nb_nodes)
shuf_fts = features[:, idx, :]
I can not find the corruption on the graph structure, why? Does this not affect the final result?
Hello, the paper said: "an explicit (stochastic) corruption function (\tilde{X}, \tilde{A}) = C(X, A)." However, in the code, I only find the corruption on node attributes: idx = np.random.permutation(nb_nodes) shuf_fts = features[:, idx, :]
I can not find the corruption on the graph structure, why? Does this not affect the final result?
thanks