approximate
Approximate ranking loss functions for the Lightning IR framework.
This module contains loss functions that use approximation techniques to compute ranking-based metrics like NDCG, MRR, and RankMSE in a differentiable manner.
Classes
|
Base class for approximate loss functions that compute ranks from scores. |
|
Approximate Mean Reciprocal Rank (MRR) loss function for ranking tasks. |
|
Approximate NDCG loss function for ranking tasks. |
|
Approximate Rank Mean Squared Error (RankMSE) loss function for ranking tasks. |