Closed SimonTopp closed 2 years ago
I don't remember ever running into this. I also don't think that I ever tried dropout in the RGCN, now that I think of it. I might have only tried that in the plain LSTMs that I was using for the multi-task experiments.
I also don't think we've run the RGCN with dropout >0. We've tested RGCN with state updating but I think just left dropout as default
Fixed in #154.
When training the RGCN on TG GPU with dropout, you get the error:
You don't get this error when setting dropout to zero. I think I've fixed it by updating the dropout mask in the forward pass as described here, but wanted to double check if this is new behavior since the training routine update PR #141. @jsadler2, have you run into this in the past/did you ever experiment with dropout? The defaults are set to 0, so I'm wondering if this has just never come up before.