Doubt about hetero conv #4464
Answered
by
rusty1s
DogitoErgoSum
asked this question in
Q&A
-
Beta Was this translation helpful? Give feedback.
Answered by
rusty1s
Apr 12, 2022
Replies: 1 comment
-
They are both performed at the same time. That is, input features to GNN layers will always correspond to the features of the previous layer, not to intermediate outputs. |
Beta Was this translation helpful? Give feedback.
0 replies
Answer selected by
DogitoErgoSum
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
They are both performed at the same time. That is, input features to GNN layers will always correspond to the features of the previous layer, not to intermediate outputs.