Salvato in:
Dettagli Bibliografici
Autori principali: Roy, Soumya, Banerjee, Soumya, Verma, Vinay, Dasgupta, Soumik, Gupta, Deepak, Rai, Piyush
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2507.03281
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915371749998592
author Roy, Soumya
Banerjee, Soumya
Verma, Vinay
Dasgupta, Soumik
Gupta, Deepak
Rai, Piyush
author_facet Roy, Soumya
Banerjee, Soumya
Verma, Vinay
Dasgupta, Soumik
Gupta, Deepak
Rai, Piyush
contents Machine unlearning (MUL) refers to the problem of making a pre-trained model selectively forget some training instances or class(es) while retaining performance on the remaining dataset. Existing MUL research involves fine-tuning using a forget and/or retain set, making it expensive and/or impractical, and often causing performance degradation in the unlearned model. We introduce {\pname}, an unlearning-aware vision transformer-based architecture that can directly perform unlearning for future unlearning requests without any fine-tuning over the requested set. The proposed model is trained by simulating unlearning during the training process itself. It involves randomly separating class(es)/sub-class(es) present in each mini-batch into two disjoint sets: a proxy forget-set and a retain-set, and the model is optimized so that it is unable to predict the forget-set. Forgetting is achieved by withdrawing keys, making unlearning on-the-fly and avoiding performance degradation. The model is trained jointly with learnable keys and original weights, ensuring withholding a key irreversibly erases information, validated by membership inference attack scores. Extensive experiments on various datasets, architectures, and resolutions confirm {\pname}'s superiority over both fine-tuning-free and fine-tuning-based methods.
format Preprint
id arxiv_https___arxiv_org_abs_2507_03281
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle NOVO: Unlearning-Compliant Vision Transformers
Roy, Soumya
Banerjee, Soumya
Verma, Vinay
Dasgupta, Soumik
Gupta, Deepak
Rai, Piyush
Computer Vision and Pattern Recognition
Machine unlearning (MUL) refers to the problem of making a pre-trained model selectively forget some training instances or class(es) while retaining performance on the remaining dataset. Existing MUL research involves fine-tuning using a forget and/or retain set, making it expensive and/or impractical, and often causing performance degradation in the unlearned model. We introduce {\pname}, an unlearning-aware vision transformer-based architecture that can directly perform unlearning for future unlearning requests without any fine-tuning over the requested set. The proposed model is trained by simulating unlearning during the training process itself. It involves randomly separating class(es)/sub-class(es) present in each mini-batch into two disjoint sets: a proxy forget-set and a retain-set, and the model is optimized so that it is unable to predict the forget-set. Forgetting is achieved by withdrawing keys, making unlearning on-the-fly and avoiding performance degradation. The model is trained jointly with learnable keys and original weights, ensuring withholding a key irreversibly erases information, validated by membership inference attack scores. Extensive experiments on various datasets, architectures, and resolutions confirm {\pname}'s superiority over both fine-tuning-free and fine-tuning-based methods.
title NOVO: Unlearning-Compliant Vision Transformers
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.03281