Data Augmentation Improves Machine Unlearning

TL;DR

This paper demonstrates that systematic data augmentation strategies can significantly enhance the effectiveness of machine unlearning methods, reducing memorization and improving privacy preservation.

Contribution

It investigates the role of augmentation design in machine unlearning, showing its impact on unlearning performance across different methods and datasets.

Findings

Proper augmentation reduces the performance gap to retrained models by up to 40.12%.

Augmentation improves unlearning effectiveness across various strategies and datasets.

Augmentation helps in reducing memorization and enhances privacy-preserving unlearning.

Abstract

Machine Unlearning (MU) aims to remove the influence of specific data from a trained model while preserving its performance on the remaining data. Although a few works suggest connections between memorisation and augmentation, the role of systematic augmentation design in MU remains under-investigated. In this work, we investigate the impact of different data augmentation strategies on the performance of unlearning methods, including SalUn, Random Label, and Fine-Tuning. Experiments conducted on CIFAR-10 and CIFAR-100, under varying forget rates, show that proper augmentation design can significantly improve unlearning effectiveness, reducing the performance gap to retrained models. Results showed a reduction of up to 40.12% of the Average Gap unlearning Metric, when using TrivialAug augmentation. Our results suggest that augmentation not only helps reduce memorization but also plays a crucial role in achieving privacy-preserving and efficient unlearning.