Question on additive aggregation weight initialization

[seungwonpark]

Hi, I have a question about weight initialization of node's additive aggregation here.

At model.py#L41, weights are initialized with torch.ones, not torch.zeros. This will make actual weights to be initialized with 0.7311, not 0.5000. Was it intended? (Though it won't affect much on training, I'm just curious about it.)

[JiaminRen]

I don't think it matters. A single parameter should be easy to optimize.

[seungwonpark]

Thanks for the comment.