🇨🇴🕸️ Add co-occurence filtered meta model #943
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
trigger ci
trigger ci
trigger ci
trigger ci
cthoyt
reviewed
May 30, 2022
cthoyt
reviewed
May 30, 2022
cthoyt
reviewed
May 30, 2022
cthoyt
reviewed
May 30, 2022
|
@PyKEEN-bot test |
trigger ci
trigger ci
cthoyt
reviewed
May 31, 2022
src/pykeen/models/baseline/utils.py
Outdated
| @@ -23,13 +23,33 @@ def get_csr_matrix( | |||
| row_indices: numpy.ndarray, | |||
| col_indices: numpy.ndarray, | |||
| shape: Tuple[int, int], | |||
| dtype: numpy.dtype = numpy.float32, | |||
| normalize: bool = True, | |||
There was a problem hiding this comment.
if you can imagine we ever want a norm besides l1, you could change this to be an Optional[str] and have set to "l1" as default
cthoyt
approved these changes
May 31, 2022
trigger ci
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Outdated suggestions cannot be applied.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 meta-model which wraps a base model and masks out scores for entities which do not co-occur with a relation (in the training set).
It can also be used to wrap an already trained model.
Similar techniques have been applied in the winning approaches of the OGB-LSC challenge, although there, valid/test triples were also included.
In theory, we could also apply some sort of (soft) masking already during training to enable the model to ignore scores which will be filtered at evaluation time anyway.