Alexander Jakob Dautel comments

Results 5 comments of


                                            Alexander Jakob Dautel

Adding user biases and item biases for implicit matrix factorization

> I'm not sure adding bias terms is a good idea because **we can't interpret cosine similarity between items,(or users) anymore** if we add bias terms. @ita9naiwa Couldn't we just...

Adding user biases and item biases for implicit matrix factorization

> https://github.com/benfred/implicit/blob/fbed6211547e676ba414fdf734432aa3252ac90b/implicit/lmf.pyx#L169-L181 Very clever way of implementing the bias terms, by the way. :)

Adding user biases and item biases for implicit matrix factorization

> > I'm not sure adding bias terms is a good idea because **we can't interpret cosine similarity between items,(or users) anymore** if we add bias terms. > > Therefore,...

Remove "-is:buried" condition

An Anki add-on with the fix in this PR is available [here](https://ankiweb.net/shared/info/1730491641).

Compatible with Binary Classification?

You call it on the logits, so should work just the same for binary classification.