Add Lambda Weights for PairWiseLoss and ListMLELoss

[LakshmiKalaKadali]

Added LambdaWeights for PairwiseLoss and ListMLELoss for list wise ranking

[gemini-code-assist]

Summary of Changes

Hello @LakshmiKalaKadali, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request introduces a comprehensive set of LambdaWeight classes and associated utility functions to enhance the Keras ecosystem's capabilities for Learning to Rank. It provides specialized weighting strategies for both pairwise and listwise ranking losses, enabling more precise optimization of ranking metrics by incorporating relevance and position information into the loss calculation.

Highlights

• New Lambda Weighting Classes: Introduced LambdaWeight as an abstract base class, along with concrete implementations: LabelDiffLambdaWeight, DCGLambdaWeight, and ListMLELambdaWeight. These classes provide flexible weighting mechanisms for various ranking loss functions.
• DCG-based Weighting: The DCGLambdaWeight class offers configurable Discounted Cumulative Gain (DCG) based weighting. It supports parameters such as topn cutoff, custom gain_fn and rank_discount_fn, normalization, and a smooth_fraction for blending with LambdaMART-style weighting.
• ListMLE Specific Weights: A ListMLELambdaWeight class has been added to provide position-based discounting specifically for List Maximum Likelihood Estimation (ListMLE) loss, emphasizing top-ranked items through a logarithmic rank discount.
• Keras 3 Compatibility: The newly added lambda weight implementations are designed to be compatible with Keras 3, ensuring seamless operation across various backends like TensorFlow, JAX, and PyTorch.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in issue comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist is currently in preview and may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments to provide feedback.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request introduces LambdaWeight classes for PairwiseLoss and ListMLELoss for list wise ranking. The review focuses on improving robustness and correctness by addressing a critical issue in ListMLELambdaWeight, a potential design issue in the LambdaWeight base class, an undocumented scaling factor in DCGLambdaWeight, and a bug in the test suite.