Charles Tapley Hoyt

Can you please give a code example that reproduces this error as well as copying the full stack trace?

I refuse to add a GO or Drugbank dataset directly to pykeen. There’s no way a set of computer science authors did anything scientifically meaningful with them.

Sure, we could probably make good arguments about all of the datasets on why they're not good. But I am an authority on biological knowledge graphs and won't let my...

@mberr how do we handle this with the abstract interface then? they seem fundamentally incompatible at the moment can we change the current implementation to use the edge index to...

@mberr this sort of demonstrates a different way to do things, since it allows r-gcn itself to be extended, but I think it's probably fine to leave this more as...

Is this an issue that the documentation lead @AmartyaCSB to put this in the wrong place? Can we find where that was and fix it?

@migalkin BAHHH

What's the roadmap for this PR? I think that it's fine to keep `score_{hrt,h,t}_inverse` inside the model - it would only appear in the base Model class, right?

We'll need the full stack trace to go along with the error you're getting otherwise it's not possible to give feedback. Additionally, please either provide either the files you used...

I'm going to close this since we never got a response from the submitter