Fair Machine Unlearning: Data Removal while Mitigating Disparities
This addresses the need for fair data deletion under regulations like GDPR, offering a novel solution for real-world applications where fairness is critical, though it builds incrementally on prior unlearning work.
The paper tackles the problem of efficiently removing data from machine learning models while maintaining fairness, showing that existing unlearning methods fail to accommodate fairness interventions and proposing a new method that provably unlearns data and preserves fairness, with experimental validation on real-world datasets.
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.