ENH Factorization Machine classifier #50
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Oh nice. I've been looking for a good TF FM implementation :) |
|
Hi @mdagost! We only have a classifier. A PR for the regressor is welcome! |
samcarlos
reviewed
Jun 13, 2017
muffnn/fm/fm_classifier.py
Outdated
| v2 = self._v * self._v | ||
| v2x2 = tf.stack([matmul(x2, v2[i, :, :]) | ||
| for i in range(self.rank)], axis=1) | ||
| int_term = 0.5 * tf.reduce_sum(tf.square(vx) - v2x2, axis=1) |
There was a problem hiding this comment.
The axis=1 is a little confusing since its in the middle of this 3-dim array. Maybe change it to axis=-1 instead?
|
Just making sure: there's no way to write eqn 1) here http://www.algo.uni-konstanz.de/members/rendle/pdf/Rendle2010FM.pdf in matrix format, is there? |
|
Yeah equation 1 is the slow version. The TF I have is the best I know of. |
|
LGTM |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR adds a factorization machine classifier.
I am going to leave the regressor for another PR.