Maciej Kula
Maciej Kula
The implementation isn't broken. It is, however, very simple: the model simply averages the embeddings of all the features it is given. Because of the averaging, the model is incapable...
Looks good, thanks for the contribution! Could you fix the `flake8` issue please?
Yes, the dependencies seem to have moved in an annoying way. I'll do my best to resolve this.
Could you please rebase on top of newest master?
Can you rebase please? Otherwise I'll close this and re-open the PR with rebased code.
I don't think so. Let me know if you find a way to do it!
There is nothing obviously wrong with the code you posted, thanks for doing the analysis. Before you start the evaluation routine on your real data, can you compare the number...
One explanation for why this would happen is if I didn't propagate the total number of items correctly across train/test splits and sequential interaction conversion (the total number of items...
That's correct. There really should be a better way of doing this but I'm short on time and GPU testing runs.
I can have a look at enabling this. In the meantime, know that pickling works!