Kumaran, M.C., Unni, M.P., Kouni, V. et al. (1 more author) (Submitted: 2026) Similarity-aware machine unlearning. [Preprint - arXiv] (Submitted)
Abstract
Machine unlearning removes the influence of user-specified training examples from a trained model, avoiding the need to retrain it from scratch. Localization-based methods improve unlearning efficiency by identifying a subset of influential model parameters. However, existing approaches select parameters based solely on forget-set importance, neglecting their role in retained dataset and often causing collateral damage to semantically similar retained examples. We address this limitation with a retain-aware localization method that considers parameter importance to both forgotten and retained data. We also introduce a retain-similar evaluation set, constructed using cosine similarity in the model embedding space, to directly measure collateral damage. Across eleven experimental settings on CIFAR-10 dataset and ResNet18 model, our method consistently reduces collateral damage while improving standard unlearning metrics, demonstrating the effectiveness of retain-aware localization for similarity-aware machine unlearning.
Metadata
| Item Type: | Preprint |
|---|---|
| Authors/Creators: |
|
| Copyright, Publisher and Additional Information: | © 2026 The Author(s). This preprint is made available under a Creative Commons Attribution 4.0 International License. (https://creativecommons.org/licenses/by/4.0/) |
| Keywords: | cs.LG; cs.LG |
| Dates: |
|
| Institution: | The University of Sheffield |
| Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
| Date Deposited: | 12 Nov 2026 15:24 |
| Last Modified: | 12 Nov 2026 15:24 |
| Status: | Submitted |
| Identification Number: | 10.48550/arXiv.2608.00246 |
| Related URLs: | |
| Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:247742 |
Download
Filename: 2608.00246v1.pdf
Licence: CC-BY 4.0
CORE (COnnecting REpositories)
CORE (COnnecting REpositories)