# Debiased Explainable Pairwise Ranking from Implicit Feedback

arXiv: https://arxiv.org/abs/2107.14768 · HTML: https://mlsanity.com/paper/2107.14768/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 55 references that are in the map.
- First posted on arXiv 30 Jul 2021.

## Builds on (most cited first, 19 of 19)

- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [Recommendations as Treatments: Debiasing Learning and Evaluation](https://mlsanity.com/paper/1602.05352/) (2016)
- [Bias and Debias in Recommender System: A Survey and Future Directions](https://mlsanity.com/paper/2010.03240/) (2020)
- [Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate](https://mlsanity.com/paper/1804.07931/) (2018)
- [VBPR: Visual Bayesian Personalized Ranking from Implicit Feedback](https://mlsanity.com/paper/1510.01784/) (2015)
- [Fast Matrix Factorization for Online Recommendation with Implicit Feedback](https://mlsanity.com/paper/1708.05024/) (2017)
- [Unbiased Recommender Learning from Missing-Not-At-Random Implicit Feedback](https://mlsanity.com/paper/1909.03601/) (2019)
- [Modeling User Exposure in Recommendation](https://mlsanity.com/paper/1510.07025/) (2015)
- [Neural Rating Regression with Abstractive Tips Generation for Recommendation](https://mlsanity.com/paper/1708.00154/) (2017)
- [Reinforced Negative Sampling over Knowledge Graph for Recommendation](https://mlsanity.com/paper/2003.05753/) (2020)
- [Large-scale Causal Approaches to Debiasing Post-click Conversion Rate Estimation with Multi-task Learning](https://mlsanity.com/paper/1910.09337/) (2019)
- [Fast Adaptively Weighted Matrix Factorization for Recommendation with Implicit Feedback](https://mlsanity.com/paper/2003.01892/) (2020)
- [Explaining Latent Factor Models for Recommendation with Influence Functions](https://mlsanity.com/paper/1811.08120/) (2018)
- [Dynamic Matrix Factorization with Priors on Unknown Values](https://mlsanity.com/paper/1507.06452/) (2015)
- [Modeling and Counteracting Exposure Bias in Recommender Systems](https://mlsanity.com/paper/2001.04832/) (2020)
- [Theoretical Modeling of the Iterative Properties of User Discovery in a Collaborative Filtering Recommender System](https://mlsanity.com/paper/2008.13526/) (2020)
- [Visually Explainable Recommendation](https://mlsanity.com/paper/1801.10288/) (2018)
- [Personalised novel and explainable matrix factorisation](https://mlsanity.com/paper/1907.11000/) (2019)
- [Human-Algorithm Interaction Biases in the Big Data Cycle: A Markov Chain Iterated Learning Framework](https://mlsanity.com/paper/1608.07895/) (2016)

## Built on by (most cited first, 7 of 7)

- [Breaking Feedback Loops in Recommender Systems with Causal Inference](https://mlsanity.com/paper/2207.01616/) (2022)
- [Cross Pairwise Ranking for Unbiased Item Recommendation](https://mlsanity.com/paper/2204.12176/) (2022)
- [Debiasing the Cloze Task in Sequential Recommendation with Bidirectional Transformers](https://mlsanity.com/paper/2301.09210/) (2023)
- [Aligning Model Evaluations with Human Preferences: Mitigating Token Count Bias in Language Model Assessments](https://mlsanity.com/paper/2407.12847/) (2024)
- [Comparing Apples to Apples: Generating Aspect-Aware Comparative Sentences from User Reviews](https://mlsanity.com/paper/2307.03691/) (2023)
- [The Importance of Causality in Decision Making: A Perspective on Recommender Systems](https://mlsanity.com/paper/2410.01822/) (2024)
- [DPR: An Algorithm Mitigate Bias Accumulation in Recommendation feedback loops](https://mlsanity.com/paper/2311.05864/) (2023)

## Abstract (arXiv)

Recent work in recommender systems has emphasized the importance of fairness, with a particular interest in bias and transparency, in addition to predictive accuracy. In this paper, we focus on the state of the art pairwise ranking model, Bayesian Personalized Ranking (BPR), which has previously been found to outperform pointwise models in predictive accuracy, while also being able to handle implicit feedback. Specifically, we address two limitations of BPR: (1) BPR is a black box model that does not explain its outputs, thus limiting the user's trust in the recommendations, and the analyst's ability to scrutinize a model's outputs; and (2) BPR is vulnerable to exposure bias due to the data being Missing Not At Random (MNAR). This exposure bias usually translates into an unfairness against the least popular items because they risk being under-exposed by the recommender system. 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. Then, we theoretically quantify additional exposure bias resulting from the explainability, and use it as a basis to propose an unbiased estimator for the ideal EBPR loss. The result is a ranking model that aptly captures both debiased and explainable user preferences. Finally, we perform an empirical study on three real-world datasets that demonstrate the advantages of our proposed models.