# DPR: An Algorithm Mitigate Bias Accumulation in Recommendation feedback loops

arXiv: https://arxiv.org/abs/2311.05864 · HTML: https://mlsanity.com/paper/2311.05864/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 46 references that are in the map.
- First posted on arXiv 10 Nov 2023.

## Builds on (most cited first, 26 of 26)

- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [Recommendations as Treatments: Debiasing Learning and Evaluation](https://mlsanity.com/paper/1602.05352/) (2016)
- [How Algorithmic Confounding in Recommendation Systems Increases Homogeneity and Decreases Utility](https://mlsanity.com/paper/1710.11214/) (2017)
- [Causal Intervention for Leveraging Popularity Bias in Recommendation](https://mlsanity.com/paper/2105.06067/) (2021)
- [A Survey on the Fairness of Recommender Systems](https://mlsanity.com/paper/2206.03761/) (2022)
- [Feedback Loop and Bias Amplification in Recommender Systems](https://mlsanity.com/paper/2007.13019/) (2020)
- [Causal Embeddings for Recommendation](https://mlsanity.com/paper/1706.07639/) (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)
- [CIRS: Bursting Filter Bubbles by Counterfactual Interactive Recommender System](https://mlsanity.com/paper/2204.01266/) (2022)
- [Simplify and Robustify Negative Sampling for Implicit Collaborative Filtering](https://mlsanity.com/paper/2009.03376/) (2020)
- [AutoML for Deep Recommender Systems: A Survey](https://mlsanity.com/paper/2203.13922/) (2022)
- [Do Offline Metrics Predict Online Performance in Recommender Systems?](https://mlsanity.com/paper/2011.07931/) (2020)
- [Cross-Batch Negative Sampling for Training Two-Tower Recommenders](https://mlsanity.com/paper/2110.15154/) (2021)
- [On the Robustness of Aspect-based Sentiment Analysis: Rethinking Model, Data, and Training](https://mlsanity.com/paper/2304.09563/) (2023)
- [Deconvolving Feedback Loops in Recommender Systems](https://mlsanity.com/paper/1703.01049/) (2017)
- [Human Interaction with Recommendation Systems](https://mlsanity.com/paper/1703.00535/) (2017)
- [ReFRS: Resource-efficient Federated Recommender System for Dynamic and Diversified User Preferences](https://mlsanity.com/paper/2207.13897/) (2022)
- [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)
- [Causal Disentangled Recommendation Against User Preference Shifts](https://mlsanity.com/paper/2303.16068/) (2023)
- [Debiased Explainable Pairwise Ranking from Implicit Feedback](https://mlsanity.com/paper/2107.14768/) (2021)
- [Bounding System-Induced Biases in Recommender Systems with A Randomized Dataset](https://mlsanity.com/paper/2303.11574/) (2023)
- [CoSam: An Efficient Collaborative Adaptive Sampler for Recommendation](https://mlsanity.com/paper/2011.07739/) (2020)
- [Detect Professional Malicious User with Metric Learning in Recommender Systems](https://mlsanity.com/paper/2205.09673/) (2022)
- [Unbiased Pairwise Learning from Implicit Feedback for Recommender Systems without Biased Variance Control](https://mlsanity.com/paper/2304.05066/) (2023)

## Abstract (arXiv)

Recommendation models trained on the user feedback collected from deployed recommendation systems are commonly biased. User feedback is considerably affected by the exposure mechanism, as users only provide feedback on the items exposed to them and passively ignore the unexposed items, thus producing numerous false negative samples. Inevitably, biases caused by such user feedback are inherited by new models and amplified via feedback loops. Moreover, the presence of false negative samples makes negative sampling difficult and introduces spurious information in the user preference modeling process of the model. Recent work has investigated the negative impact of feedback loops and unknown exposure mechanisms on recommendation quality and user experience, essentially treating them as independent factors and ignoring their cross-effects. To address these issues, we deeply analyze the data exposure mechanism from the perspective of data iteration and feedback loops with the Missing Not At Random (MNAR) assumption, theoretically demonstrating the existence of an available stabilization factor in the transformation of the exposure mechanism under the feedback loops. We further propose Dynamic Personalized Ranking (DPR), an unbiased algorithm that uses dynamic re-weighting to mitigate the cross-effects of exposure mechanisms and feedback loops without additional information. Furthermore, we design a plugin named Universal Anti-False Negative (UFN) to mitigate the negative impact of the false negative problem. We demonstrate theoretically that our approach mitigates the negative effects of feedback loops and unknown exposure mechanisms. Experimental results on real-world datasets demonstrate that models using DPR can better handle bias accumulation and the universality of UFN in mainstream loss methods.