# Fair Machine Unlearning: Data Removal while Mitigating Disparities

arXiv: https://arxiv.org/abs/2307.14754 · HTML: https://mlsanity.com/paper/2307.14754/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 27 of its 50 references that are in the map.
- First posted on arXiv 27 Jul 2023.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 27 of 27)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [A Reductions Approach to Fair Classification](https://mlsanity.com/paper/1803.02453/) (2018)
- [Certified Data Removal from Machine Learning Models](https://mlsanity.com/paper/1911.03030/) (2019)
- [Making AI Forget You: Data Deletion in Machine Learning](https://mlsanity.com/paper/1907.05012/) (2019)
- [Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness](https://mlsanity.com/paper/1711.05144/) (2017)
- [Remember What You Want to Forget: Algorithms for Machine Unlearning](https://mlsanity.com/paper/2103.03279/) (2021)
- [Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment](https://mlsanity.com/paper/1610.08452/) (2016)
- [Differential Privacy Has Disparate Impact on Model Accuracy](https://mlsanity.com/paper/1905.12101/) (2019)
- [Descent-to-Delete: Gradient-Based Methods for Machine Unlearning](https://mlsanity.com/paper/2007.02923/) (2020)
- [Approximate Data Deletion from Machine Learning Models](https://mlsanity.com/paper/2002.10077/) (2020)
- [Minimax Pareto Fairness: A Multi Objective Perspective](https://mlsanity.com/paper/2011.01821/) (2020)
- [DeltaGrad: Rapid retraining of machine learning models](https://mlsanity.com/paper/2006.14755/) (2020)
- [A Convex Framework for Fair Regression](https://mlsanity.com/paper/1706.02409/) (2017)
- [Fairness in Recommendation Ranking through Pairwise Comparisons](https://mlsanity.com/paper/1903.00780/) (2019)
- [Degenerate Feedback Loops in Recommender Systems](https://mlsanity.com/paper/1902.10730/) (2019)
- [PUMA: Performance Unchanged Model Augmentation for Training Data Removal](https://mlsanity.com/paper/2203.00846/) (2022)
- [On the relation between accuracy and fairness in binary classification](https://mlsanity.com/paper/1505.05723/) (2015)
- [Disparate Impact in Differential Privacy from Gradient Misalignment](https://mlsanity.com/paper/2206.07737/) (2022)
- [Inductive Graph Unlearning](https://mlsanity.com/paper/2304.03093/) (2023)
- [Understanding Instance-Level Impact of Fairness Constraints](https://mlsanity.com/paper/2206.15437/) (2022)
- [A Stochastic Optimization Framework for Fair Risk Minimization](https://mlsanity.com/paper/2102.12586/) (2021)
- [Fairness without Imputation: A Decision Tree Approach for Fair Prediction with Missing Values](https://mlsanity.com/paper/2109.10431/) (2021)
- [Algorithm Fairness in AI for Medicine and Healthcare](https://mlsanity.com/paper/2110.00603/) (2021)
- [To Be Forgotten or To Be Fair: Unveiling Fairness Implications of Machine Unlearning Methods](https://mlsanity.com/paper/2302.03350/) (2023)
- [Towards Bridging the Gaps between the Right to Explanation and the Right to be Forgotten](https://mlsanity.com/paper/2302.04288/) (2023)

## Built on by (most cited first, 26 of 26)

- [SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation](https://mlsanity.com/paper/2310.12508/) (2023)
- [MUSE: Machine Unlearning Six-Way Evaluation for Language Models](https://mlsanity.com/paper/2407.06460/) (2024)
- [Rethinking Machine Unlearning for Large Language Models](https://mlsanity.com/paper/2402.08787/) (2024)
- [UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models](https://mlsanity.com/paper/2402.11846/) (2024)
- [Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement](https://mlsanity.com/paper/2409.19732/) (2024)
- [Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning](https://mlsanity.com/paper/2403.07362/) (2024)
- [Decoupled Distillation to Erase: A General Unlearning Method for Any Class-centric Tasks](https://mlsanity.com/paper/2503.23751/) (2025)
- [Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Models](https://mlsanity.com/paper/2409.11219/) (2024)
- [FairSISA: Ensemble Post-Processing to Improve Fairness of Unlearning in LLMs](https://mlsanity.com/paper/2312.07420/) (2023)
- [Position: Bridge the Gaps between Machine Unlearning and AI Regulation](https://mlsanity.com/paper/2502.12430/) (2025)
- [CURE4Rec: A Benchmark for Recommendation Unlearning with Deeper Influence](https://mlsanity.com/paper/2408.14393/) (2024)
- [How Data Inter-connectivity Shapes LLMs Unlearning: A Structural Unlearning Perspective](https://mlsanity.com/paper/2406.16810/) (2024)
- [Debiasing Machine Unlearning with Counterfactual Examples](https://mlsanity.com/paper/2404.15760/) (2024)
- [Exploring Fairness in Educational Data Mining in the Context of the Right to be Forgotten](https://mlsanity.com/paper/2405.16798/) (2024)
- [Enabling Group Fairness in Graph Unlearning via Bi-level Debiasing](https://mlsanity.com/paper/2505.09702/) (2025)
- [Operationalizing the Blueprint for an AI Bill of Rights: Recommendations for Practitioners, Researchers, and Policy Makers](https://mlsanity.com/paper/2407.08689/) (2024)
- [Data Deletion for Linear Regression with Noisy SGD](https://mlsanity.com/paper/2410.09311/) (2024)
- [NOVO: Unlearning-Compliant Vision Transformers](https://mlsanity.com/paper/2507.03281/) (2025)
- [Unlearning Algorithmic Biases over Graphs](https://mlsanity.com/paper/2505.14945/) (2025)
- [Soft Weighted Machine Unlearning](https://mlsanity.com/paper/2505.18783/) (2025)
- [Machine Unlearning of Traffic State Estimation and Prediction](https://mlsanity.com/paper/2507.17984/) (2025)
- [FedShard: Federated Unlearning with Efficiency Fairness and Performance Fairness](https://mlsanity.com/paper/2508.09866/) (2025)
- [Bias-Aware Machine Unlearning: Towards Fairer Vision Models via Controllable Forgetting](https://mlsanity.com/paper/2509.07456/) (2025)
- [Controllable Machine Unlearning via Gradient Pivoting](https://mlsanity.com/paper/2510.19226/) (2025)
- [The Tokens Remember: When Tokenization Bypasses Knowledge Editing and Unlearning](https://mlsanity.com/paper/2609.29045/) (2026)
- [Modeling Deletion Requests in Machine Unlearning](https://mlsanity.com/paper/2610.04310/) (2026)

## Abstract (arXiv)

The Right to be Forgotten is a core principle outlined by regulatory frameworks such as the EU's General Data Protection Regulation (GDPR). This principle allows individuals to request that their personal data be deleted from deployed machine learning models. While "forgetting" can be naively achieved by retraining on the remaining dataset, it is computationally expensive to do to so with each new request. As such, several machine unlearning methods have been proposed as efficient alternatives to retraining. These methods aim to approximate the predictive performance of retraining, but fail to consider how unlearning impacts other properties critical to real-world applications such as fairness. In this work, we demonstrate that most efficient unlearning methods cannot accommodate popular fairness interventions, and we propose the first fair machine unlearning method that can efficiently unlearn data instances from a fair objective. We derive theoretical results which demonstrate that our method can provably unlearn data and provably maintain fairness performance. Extensive experimentation with real-world datasets highlight the efficacy of our method at unlearning data instances while preserving fairness.