{"ID":2878759,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.18502","arxiv_id":"2508.18502","title":"Data Augmentation Improves Machine 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.","short_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...","url_abs":"https://arxiv.org/abs/2508.18502","url_pdf":"https://arxiv.org/pdf/2508.18502v1","authors":"[\"Andreza M. C. Falcao\",\"Filipe R. Cordeiro\"]","published":"2025-08-25T21:17:25Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[]","has_code":false}