Fast sLCWA #816
Open
Fast sLCWA #816
Conversation
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
trigger ci
Merged
migalkin
reviewed
Mar 8, 2022
Draft
mberr
added a commit
that referenced
this pull request
Oct 26, 2024
This PR does some pretty nice refactoring, including: 1. Taking instance generation out of the triples factory classes (borrowed from #816) 2. moving the contents of `pykeen.nn.compute_kernel` into `pykeen.utils`. This was just one function. 3. Reorganizing the text encoder and image encoder in `pykeen.nn` into submodules. Did a bit of renaming to be more consistent. --------- Co-authored-by: Max Berrendorf <max.berrendorf@gmail.com>
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Outdated suggestions cannot be applied.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 aims at adding fast sLCWA training to PyKEEN.
For this, we exploit that negative samples are created by corruption, and thus share some parts of the triple, e.g., (h, r), with the positive triple. This allows saving computation. Such optimizations already exist is other packages, e.g.,
mode="tail-batch"combine="_sp_"Tasks
score_{h,r,t}sto score multiple heads/relations/tails at onceDependencies: