Search Results for author:
Found 4 papers, 3 papers with code
Debiasing the Cloze Task in Sequential Recommendation with Bidirectional Transformers
The most common approach to mitigating exposure bias in recommendation has been Inverse Propensity Scoring (IPS), which consists of down-weighting the interacted predictions in the loss function in proportion to their propensities of exposure, yielding a theoretically unbiased learning.
Debiased Explainable Pairwise Ranking from Implicit Feedback
In this work, we first propose a novel explainable loss function and a corresponding Matrix Factorization-based model called Explainable Bayesian Personalized Ranking (EBPR) that generates recommendations along with item-based explanations.
Theoretical Modeling of the Iterative Properties of User Discovery in a Collaborative Filtering Recommender System
We present a theoretical framework to model the asymptotic evolution of the different components of a recommender system operating within a feedback loop setting, and derive theoretical bounds and convergence properties on quantifiable measures of the user discovery and blind spots.
Modeling and Counteracting Exposure Bias in Recommender Systems
Then we model the exposure that is borne from the interaction between the user and the recommender system and propose new debiasing strategies for these systems.
