Debiasing Machine Unlearning with Counterfactual Examples

arXiv:2404.15760v1 Announce Type: new
Abstract: The right to be forgotten (RTBF) seeks to safeguard individuals from the enduring effects of their historical actions by implementing machine-learning techniques. These techniques facilitate the deletion of previously acquired knowledge without requiring extensive model retraining. However, they often overlook a critical issue: unlearning processes bias. This bias emerges from two main sources: (1) data-level bias, characterized by uneven data removal, and (2) algorithm-level bias, which leads to the contamination of the remaining dataset, thereby …

abstract acquired arxiv bias counterfactual cs.ai cs.lg effects examples however issue knowledge machine model retraining processes retraining stat.ml type unlearning