DUCK: Distance-based Unlearning via Centroid Kinematics

arXiv:2312.02052v2 Announce Type: replace-cross
Abstract: Machine Unlearning is rising as a new field, driven by the pressing necessity of ensuring privacy in modern artificial intelligence models. This technique primarily aims to eradicate any residual influence of a specific subset of data from the knowledge acquired by a neural model during its training. This work introduces a novel unlearning algorithm, denoted as Distance-based Unlearning via Centroid Kinematics (DUCK), which employs metric learning to guide the removal of samples matching the nearest …

abstract acquired artificial artificial intelligence arxiv cs.cv cs.lg data influence intelligence knowledge machine modern privacy residual training type unlearning via work