Attribute-to-Delete: Machine Unlearning via Datamodel Matching
Attribute-to-Delete: Machine Unlearning via Datamodel Matching
Machine unlearning -- efficiently removing the effect of a small "forget set" of training data on a pre-trained machine learning model -- has recently attracted significant research interest. Despite this interest, however, recent work shows that existing machine unlearning techniques do not hold up to thorough evaluation in non-convex settings. …