Metraipolis › archive › dc_71c7ebb6ff69
Forget or Fine-tune? A Comparative Study of Machine Unlearning Strategies for Noisy Label Correction — arXiv:2608.30046
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.30046
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T07:52:22.993Z
- SHA-256 of the archived text
5af86fd46cffee1b0b4208a1be9daf637ccc8e2a8999e4155435390ba6580772- Stable URL of this page
https://metraipolis.com/documento/dc_71c7ebb6ff69
How to cite
Forget or Fine-tune? A Comparative Study of Machine Unlearning Strategies for Noisy Label Correction — arXiv:2608.30046 — arXiv (en), https://arxiv.org/abs/2608.30046 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_71c7ebb6ff69 (Metraipolis archive dc_71c7ebb6ff69, sha256 5af86fd46cffee1b0b4208a1be9daf637ccc8e2a8999e4155435390ba6580772)
BibTeX
@misc{dc71c7ebb6ff69,
title = {Forget or Fine-tune? A Comparative Study of Machine Unlearning Strategies for Noisy Label Correction — arXiv:2608.30046},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.30046},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_71c7ebb6ff69; sha256 5af86fd46cffee1b0b4208a1be9daf637ccc8e2a8999e4155435390ba6580772},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30046. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Noisy labels remain a critical challenge for training deep neural networks, since memorizing incorrect labels degrades generalization. Once noisy samples are identified after training, the standard solution is to retrain the model from scratch on the cleaned dataset, which is increasingly expensive as datasets and models grow. Machine Unlearning (MU) has recently emerged as a computationally efficient alternative, but the relative effectiveness of different MU strategies for noisy-label correction remains poorly understood. In this work, we conduct a comparative empirical study of five MU methods (NegGrad, Fine-Tuning (FT), Random Labeling (RL), SalUn, and MUNBa) across symmetric, asymmetric, instance-dependent, and open-set noise on CIFAR-10, CIFAR-100, and the real-world noisy dataset Food-101N. Our central finding is that the appropriate unlearning strategy is conditioned on the noise structure. Simple FT is a strong baseline across most closed-set scenarios; RL and SalUn are the most consistently robust methods and, under instance-dependent noise, approach retraining accuracy at a fraction of the computational cost; MUNBa shows advantages mainly under extreme symmetric noise. Under open-set noise, in contrast, we show that retraining on the cleaned subset degrades accuracy relative to the noisy baseline, so approximating the retrained model is not an adequate objective in this regime. On Food-101N, all MU methods remain competitive and achieve accuracies close to retraining despite reducing runtime by an order of magnitude. These findings provide practical guidelines for selecting MU strategies for post-training noisy-label correction. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.30046 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T07:28:26.820Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).