Graph-convolutional icon indicating copy to clipboard operation
Graph-convolutional copied to clipboard

Issues on graph.py

Open CHELSEA234 opened this issue 6 years ago • 1 comments

I appreciate your neat Pytorch code, but I think you may have some issues regarding code in graph.py.

In the original paper, we are supposed to have three different weights for different edge categories (equation 2). However, your code only offers one single weight matrix (line 33 in graph.py).

CHELSEA234 avatar Jun 23 '19 08:06 CHELSEA234

@CHELSEA234 ,

Hi, it's been a long time since you open this issue, not sure if you can remind these details...

I think the transformation matrixes for the three kinds of edge were implemented via the self.V_in, self.V_out and self.W_self_loop, see line-33, line-46 and line-58 in graph.py. Are you on the master branch?

LiUzHiAn avatar Aug 31 '21 08:08 LiUzHiAn