Rohan Das

@ngoyal2707 and/or @myleott , any pointers would be really helpful!

@rusty1s I would like to use RGCN for a link prediction task with just one node type but 5 different edge types. 1. What should I pass to the `edge_index`...

Thanks @rusty1s! Right, I am only including negative samples during training, so I need to map to 6 different classes, where 0 corresponds to the negative edge or no edge...

No, you are right. I don't want to use negative edges for message passing. From what I understand, if I have 5 positive edges and add negative edges during training,...

Thank you so much! This makes sense to me now. Just one last follow-up if it's okay. Looking at the example again: https://github.com/pyg-team/pytorch_geometric/blob/e213c297bb2aeb9ac50db258f5ab01ea11aea349/examples/rgcn_link_pred.py#L92C1-L95C68 Why is the same `data.edge_train_type` (which I...