Metraipolis › archive › dc_07f21ae1fc3d

UnAct: Gradient-Free Unlearning via Targeted Activation Intervention — arXiv:2610.04426

Source
arXiv
Original
https://arxiv.org/abs/2610.04426
License (as archived)
CC0-1.0
Archived
2026-10-06T05:30:34.219Z
SHA-256 of the archived text
63efcd3e125b920a231daedcdbe8668cf3f095555b280809d75587c768728581
Stable URL of this page
https://metraipolis.com/documento/dc_07f21ae1fc3d

How to cite

UnAct: Gradient-Free Unlearning via Targeted Activation Intervention — arXiv:2610.04426 — arXiv, https://arxiv.org/abs/2610.04426 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_07f21ae1fc3d (Metraipolis archive dc_07f21ae1fc3d, sha256 63efcd3e125b920a231daedcdbe8668cf3f095555b280809d75587c768728581)
BibTeX
@misc{dc07f21ae1fc3d,
  title = {UnAct: Gradient-Free Unlearning via Targeted Activation Intervention — arXiv:2610.04426},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.04426},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_07f21ae1fc3d; sha256 63efcd3e125b920a231daedcdbe8668cf3f095555b280809d75587c768728581},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04426. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Machine unlearning seeks to remove the influence of designated training data from a trained model without retraining from scratch. Retrain-free methods such as Selective Synaptic Dampening (SSD) and its label-free variant LFSSD avoid full retraining but still require backpropagation and parameter importance computed over the entire dataset. We ask: what happens when a deletion request arrives with only a few images of the class to be forgotten? To answer this question, we introduce UnAct, a gradient-free class-unlearning method that needs only forward passes over the forget images. UnAct scores late-layer units by their responses, attenuates the most responsive connections, and repeats this for up to 20 rounds using no gradients, no labels, and no retained data. On ResNet-18 trained with CIFAR-10, CIFAR-20, and CIFAR-100, UnAct is competitive with SSD and LFSSD when forgetting entire classes and, unlike them, never collapses the network when forget data is scarce. On ResNet-18, across all tested sizes, UnAct's retain accuracy stays within 2.5 points of retraining, while SSD and LFSSD, at their full-class operating points, lose up to 86 points on some classes. With five forget images on CIFAR-10, UnAct's distance to retraining is 0.21 points, against 67 for LFSSD and 90 for SSD, and re-selecting SSD's threshold at each size with an oracle does not close the gap. In preliminary transfer to ViT-B/16, UnAct's distance to retraining is 11.5 against 33.7 for SSD, and a request is 19x faster than SSD when SSD computes its importance at request time. The code is available at this https URL

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.04426 — 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 2026-10-06T05:27:05.682Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).