Pinned Loading

1. user_preference_modeling user_preference_modeling Public

   Multiple ways to model user preference in recommender systems

   Python 18 4

2. causal_debiased_ranking causal_debiased_ranking Public

   We will show how to factorize and debias ranking to improve personalization and reduce popularity bias both on item side and to reduce the dominance of power users.

   Python 7 4

3. two_tower_models two_tower_models Public

   We write sample code for two tower models for retrieval and add RLHF/RLAIF style alignment with a ranking model to make the retrieval more aligned with the ranking model on top

   Python 113 21

4. kd_early_ranker kd_early_ranker Public

   Covers a couple of approaches to training an early ranker with knowledge distillation from final ranker

   Python 2 3

5. pipelined_early_ranker pipelined_early_ranker Public

   Pipelined early ranker in a recommender system

   Python 1 3

6. reward_maximizing_ranking reward_maximizing_ranking Public

   Adding REINFORCE based reward maximization to pointwise ranking

   Python 4 3