Fair Machine Unlearning: Data Removal while Mitigating Disparities

TL;DR

This paper introduces a novel fair machine unlearning method that efficiently removes data from models while maintaining fairness, addressing a critical gap in existing unlearning techniques.

Contribution

The paper proposes the first unlearning method that preserves fairness, with theoretical guarantees and extensive empirical validation.

Findings

Efficient unlearning while maintaining fairness is achievable.

Most existing unlearning methods cannot handle fairness constraints.

The proposed method outperforms baselines in fairness and unlearning accuracy.

Abstract

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.