lightaime/deep_gcns_torch

In the class GENConv, should the output dimension of edge_encoder be in_dim instead of emb_dim?

youngleec opened this issue · 1 comments

youngleec commented

Hi, your work is great and interests me a lot.

In the class GENConv, should the output dimension of edge_encoder be in_dim instead of emb_dim, especially when the in_dim doesn't equal to the emb_dim? Thanks.

deep_gcns_torch/gcn_lib/sparse/torch_vertex.py

Line 57 in 03d553d

self.edge_encoder = torch.nn.Linear(edge_feat_dim, emb_dim)

lightaime commented

Hi @youngleec. You are right. It should be in_dim instead of emb_dim for the case when in_dim != emb_dim. I noticed this and fixed it when I created a pull request for PyG (pyg-team/pytorch_geometric@a173c07). But I forgot to change it here. Thanks for your reminder.