Exploring Nonlinear Pathway in Parameter Space for Machine Unlearning

arXiv:2505.10859v2 Announce Type: replace Abstract: Machine Unlearning (MU) aims to remove the information of specific training data from a trained model, ensuring compliance with privacy regulations and user requests. While one line of existing MU methods relies on linear parameter updates via task arithmetic, they suffer from weight entanglement. In this work, we propose a novel MU framework called Mode Connectivity Unlearning (MCU) that leverages mode connectivity to find an unlearning pathwa