Closed ChangminWu closed 3 years ago
Hi! You can think of root_emb
as the self-edge feature (connecting from the node to the same node). We just replaced edge_attr
with root_emb
here.
I have not tested other modeling choices, but I do not think this is so essential to the model performance.
Now I see... Thanks a lot for the explanation!
Hi,
I am a bit confused by your implementation of GCN in the examples for the graph property prediction task. For example, in
ogb/examples/graphproppred/mol/conv.py
, you wrote GCN message-passing asI don't quite understand the role of
self.root_emb
in this line of code. To me, this layer seems to be of the same function as the bias in the previous linear transform ofx
... Could you please explain in more details why this embedding layer is useful here? Is it a way to improve the performance of GCN?Thank you!