Preprint
Jul 2026
Similarity-Aware Machine Unlearning
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 o...
Madhavan Citalamangalam Kumaran, M. P. Unni, Vicky Kouni et al.
· 0 citations