Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2508.18502 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918130574426112 |
|---|---|
| author | Falcao, Andreza M. C. Cordeiro, Filipe R. |
| author_facet | Falcao, Andreza M. C. Cordeiro, Filipe R. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_18502 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Data Augmentation Improves Machine Unlearning Falcao, Andreza M. C. Cordeiro, Filipe R. Machine Learning Artificial Intelligence 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. |
| title | Data Augmentation Improves Machine Unlearning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2508.18502 |