LMEraser: Large Model Unlearning through Adaptive Prompt Tuning

arXiv:2404.11056v1 Announce Type: cross
Abstract: To address the growing demand for privacy protection in machine learning, we propose a novel and efficient machine unlearning approach for \textbf{L}arge \textbf{M}odels, called \textbf{LM}Eraser. Existing unlearning research suffers from entangled training data and complex model architectures, incurring extremely high computational costs for large models. LMEraser takes a divide-and-conquer strategy with a prompt tuning architecture to isolate data influence. The training dataset is partitioned into public and private datasets. Public data are used to train …

arxiv cs.ai cs.cr cs.lg large prompt