PCRL handles unknown users and/or items#451
Open
vlainic wants to merge 1146 commits intoPreferredAI:masterfrom
Open
PCRL handles unknown users and/or items#451vlainic wants to merge 1146 commits intoPreferredAI:masterfrom
vlainic wants to merge 1146 commits intoPreferredAI:masterfrom
Conversation
I just used the same code construction as for MCF.score, as they both have item graph modality. The local tests worked.
I had some bugs too on my side when deploying, and this fixed the problem. Hopefully this review will not fail.
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
9 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
I have changed
recom_pcrl.pyfollowing the example ofrecom_mcf.py, as they have the same modality. I run a test locally on my data and it worked fine.I did this following #444 as I could not understand why PCRL does not handle this, while all others I have tried to. You made all models just
raise ScoreExceptionand then make it a default score. After reading the PCRL paper, I could not understand why it couldn't handle unknown users or items as any other model here. TBH, I think that all models with modalities should somehow handle cold-start, even with the global mean.Related Issues
As I mentioned above, this is related to the Issue #444 .
Checklist:
README.md(if you are adding a new model).examples/README.md(if you are adding a new example).datasets/README.md(if you are adding a new dataset).