# Privacy-Utility-Bias Trade-offs for Privacy-Preserving Recommender Systems

arXiv: https://arxiv.org/abs/2511.22515 · HTML: https://mlsanity.com/paper/2511.22515/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 73 references that are in the map.
- First posted on arXiv 27 Nov 2025.

## Builds on (most cited first, 25 of 25)

- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [Carbon Emissions and Large Neural Network Training](https://mlsanity.com/paper/2104.10350/) (2021)
- [Differential Privacy Has Disparate Impact on Model Accuracy](https://mlsanity.com/paper/1905.12101/) (2019)
- [Variational Autoencoders for Collaborative Filtering](https://mlsanity.com/paper/1802.05814/) (2018)
- [Recommendations as Treatments: Debiasing Learning and Evaluation](https://mlsanity.com/paper/1602.05352/) (2016)
- [Collecting Telemetry Data Privately](https://mlsanity.com/paper/1712.01524/) (2017)
- [When the Curious Abandon Honesty: Federated Learning Is Not Private](https://mlsanity.com/paper/2112.02918/) (2021)
- [The Unfairness of Popularity Bias in Recommendation](https://mlsanity.com/paper/1907.13286/) (2019)
- [A Survey on Trustworthy Recommender Systems](https://mlsanity.com/paper/2207.12515/) (2022)
- [User-centered Evaluation of Popularity Bias in Recommender Systems](https://mlsanity.com/paper/2103.06364/) (2021)
- [Evaluations of Machine Learning Privacy Defenses are Misleading](https://mlsanity.com/paper/2404.17399/) (2024)
- [The Connection Between Popularity Bias, Calibration, and Fairness in Recommendation](https://mlsanity.com/paper/2008.09273/) (2020)
- [Understanding Biases in ChatGPT-based Recommender Systems: Provider Fairness, Temporal Stability, and Recency](https://mlsanity.com/paper/2401.10545/) (2024)
- [Fast Differentially Private Matrix Factorization](https://mlsanity.com/paper/1505.01419/) (2015)
- [Measuring Personalization of Web Search](https://mlsanity.com/paper/1706.05011/) (2017)
- [Unlearning Protected User Attributes in Recommendations with Adversarial Training](https://mlsanity.com/paper/2206.04500/) (2022)
- [The Unfairness of Popularity Bias in Book Recommendation](https://mlsanity.com/paper/2202.13446/) (2022)
- [A Comprehensive Survey of Evaluation Techniques for Recommendation Systems](https://mlsanity.com/paper/2312.16015/) (2023)
- [Fast Multi-Step Critiquing for VAE-based Recommender Systems](https://mlsanity.com/paper/2105.00774/) (2021)
- [Item Recommendation with Variational Autoencoders and Heterogenous Priors](https://mlsanity.com/paper/1807.06651/) (2018)
- [Private Matrix Factorization with Public Item Features](https://mlsanity.com/paper/2309.11516/) (2023)
- [The Impact of Differential Privacy on Recommendation Accuracy and Popularity Bias](https://mlsanity.com/paper/2401.03883/) (2024)
- [A Personalized Framework for Consumer and Producer Group Fairness Optimization in Recommender Systems](https://mlsanity.com/paper/2402.00485/) (2024)
- [Differentially Private User-based Collaborative Filtering Recommendation Based on K-means Clustering](https://mlsanity.com/paper/1812.01782/) (2018)

## Built on by (most cited first, 2 of 2)

- [Position: Embodied AI Requires a Privacy-Utility Trade-off](https://mlsanity.com/paper/2605.05017/) (2026)
- [Rethinking Fairness in LLM-Based Recommender Systems: A Survey](https://mlsanity.com/paper/2606.28340/) (2026)

## Abstract (arXiv)

Recommender systems (RSs) output ranked lists of items, such as movies or restaurants, that users may find interesting, based on the user's past ratings and ratings from other users. RSs increasingly incorporate differential privacy (DP) to protect user data, raising questions about how privacy mechanisms affect both recommendation accuracy and fairness. We conduct a comprehensive, cross-model evaluation of two DP mechanisms, differentially private stochastic gradient descent (DPSGD) and local differential privacy (LDP), applied to four recommender systems (Neural Collaborative Filtering (NCF), Bayesian Personalized Ranking (BPR), Singular Value Decomposition (SVD), and Variational Autoencoder (VAE)) on the MovieLens-1M and Yelp datasets. We find that stronger privacy consistently reduces utility, but not uniformly. NCF under DPSGD shows the smallest accuracy loss (under 10 percent at epsilon approximately 1), whereas SVD and BPR experience larger drops, especially for users with niche preferences. VAE is the most sensitive to privacy, with sharp declines for sparsely represented groups. The impact on bias metrics is similarly heterogeneous. DPSGD generally reduces the gap between recommendations of popular and less popular items, whereas LDP preserves existing patterns more closely. These results highlight that no single DP mechanism is uniformly superior; instead, each provides trade-offs under different privacy regimes and data conditions.