Add weighted regularization about kge HOT 8 CLOSED

This is also easly solved by only computing a penalty for the parameters that were used in the batch, see https://github.com/facebookresearch/kbc/blob/master/kbc/regularizers.py

from kge.

Hmm, is the link you send actually correct? It should also matter how often the parameter is used in a batch.

from kge.

I am unassigning this from me (and, in fact, afaik Daniel was on this).

from kge.

factors is the batch of entities or relations, so if an entity/relation occurs multiple times will amount to it being weighted according to its frequency.

from kge.

Sounds good. Enabling this way of weighted regularization could be a separate regularizer (e.g., "sparse_l2"). Note that here one may need to proceed differently to stay independent of the batch size (see #35): the penalty term (in its implementation) needs to be scaled such that it its expectation is independent of the batch size.

from kge.

Yes, in fact this is what they do in their implementation, they divide the penalty term by batch size.

from kge.

Yep, this sounds good.

from kge.

I am closing this, discussion of this feature is in #41.

from kge.