I'm currently working on the raindrop architecture, and I have a couple of questions regarding your implementation of the message passing algorithm included here:
The first is where is the message_selfattention method (implementing as far as I can read the attention mechanism described in the paper) used in the code. I tried inspecting it in detail, but I couldn't find any calls to it, or methods with that name in the underlying MessagePassing class from pyg.
The second relates to the L2 regularization parameter on the distances between the graphs. It seems that the computation of the distance is not used in the file (local_structure_regularization, line 319). Is the regulariser used and called elsewhere? Or was it removed in later iterations of the model?
Hi all, and thanks for such a great paper!
I'm currently working on the raindrop architecture, and I have a couple of questions regarding your implementation of the message passing algorithm included here:
The first is where is the message_selfattention method (implementing as far as I can read the attention mechanism described in the paper) used in the code. I tried inspecting it in detail, but I couldn't find any calls to it, or methods with that name in the underlying MessagePassing class from pyg.
The second relates to the L2 regularization parameter on the distances between the graphs. It seems that the computation of the distance is not used in the file (
local_structure_regularization, line 319). Is the regulariser used and called elsewhere? Or was it removed in later iterations of the model?Best, and thank you very much once again! Lucas