Machine unlearning through fine-grained model parameters perturbation

arXiv:2401.04385v2 Announce Type: replace
Abstract: Machine unlearning techniques, which involve retracting data records and reducing influence of said data on trained models, help with the user privacy protection objective but incur significant computational costs. Weight perturbation-based unlearning is a general approach, but it typically involves globally modifying the parameters. We propose fine-grained Top-K and Random-k parameters perturbed inexact machine unlearning strategies that address the privacy needs while keeping the computational costs tractable.
In order to demonstrate the efficacy of our …

abstract arxiv computational costs cs.ai cs.lg data fine-grained general influence machine parameters privacy protection records through type unlearning