Efficient Machine Unlearning by Model Splitting and Core Sample Selection
This addresses the challenge of machine unlearning for legal compliance, offering a more efficient and verifiable solution compared to existing methods.
The paper tackles the problem of efficiently and verifiably removing specific data from machine learning models to meet legal requirements like the right to be forgotten, introducing a generalized unlearning metric and a training procedure called MaxRR that enables exact unlearning in many cases or closely matches full retraining otherwise.
Machine unlearning is essential for meeting legal obligations such as the right to be forgotten, which requires the removal of specific data from machine learning models upon request. While several approaches to unlearning have been proposed, existing solutions often struggle with efficiency and, more critically, with the verification of unlearning - particularly in the case of weak unlearning guarantees, where verification remains an open challenge. We introduce a generalized variant of the standard unlearning metric that enables more efficient and precise unlearning strategies. We also present an unlearning-aware training procedure that, in many cases, allows for exact unlearning. We term our approach MaxRR. When exact unlearning is not feasible, MaxRR still supports efficient unlearning with properties closely matching those achieved through full retraining.