Add RankNetLoss #7
Merged
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
|
Hi @tomaarsen, I've added RankNetLoss. |
tomaarsen
force-pushed
the
feat/cross_encoder_trainer
branch
from
c1dc495 to
79f9e22
Compare
It's a bit confusing to include the weighting scheme in the config if the RankNet loss doesn't have a notion of that
|
I think this is looking great! I'm merging it now 🤗
|
|
Thank you and great work!! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.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.
RankNetLoss Implementation for Cross Encoder Trainer
This PR adds RankNetLoss functionality to the Cross Encoder Trainer feature.
Changes
Implementation Details
RankNetLoss is a pairwise loss function which learns a ranking function by optimizing pairwise document comparisons using a neural network.
The implementation inherits from the LambdaLoss base class and uses a NoWeightingScheme, focusing solely on the pairwise comparison of documents.
The loss function implements the core RankNet algorithm from the Burges et al. paper (2005), which uses gradient descent to learn a ranking function by optimizing a probabilistic cost function based on pairwise document comparisons.
Reference: https://icml.cc/Conferences/2015/wp-content/uploads/2015/06/icml_ranking.pdf