arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2411.08443cs.LGcs.CV
收藏

通过LoRA实现预训练模型的残差特征对齐机器去学习

Machine Unlearning on Pre-trained Models by Residual Feature Alignment Using LoRA

City University of Macau(澳门城市大学)

Laiqiao Qin, Tianqing Zhu, Linlin Wang, Wanlei Zhou

AI总结:

本文提出一种高效的预训练模型去学习方法,通过LoRA分解中间特征并调整残差特征,实现去学习与保留目标的对齐,实验验证了方法的有效性。

摘要:

机器去学习是一种新兴技术,旨在从已训练模型中移除一部分训练数据,而不显著影响模型在剩余数据上的性能。该技术在保护用户隐私和消除有害或过时数据方面变得越来越重要。关键挑战在于有效且高效地去学习特定信息而不影响模型在保留数据上的实用性。对于预训练模型,微调是实现去学习目标的重要方法。以往的工作通常微调整个模型的参数,这带来了显著的计算成本。此外,微调过程可能导致中间层特征的偏移,影响模型的整体实用性。在本文中,我们提出了一种新颖且高效的预训练模型去学习方法。我们称之为残差特征对齐去学习。具体而言,我们利用LoRA(低秩适应)将模型的中间特征分解为预训练特征和残差特征。通过调整残差特征,我们对齐去学习模型与预训练模型在中间特征层面,以实现去学习和保留目标。该方法旨在学习保留集上的零残差和去学习集上的偏移残差。在多个数据集上的广泛实验验证了我们方法的有效性。

英文摘要:

Machine unlearning is an emerging technology that removes a subset of the training data from a trained model without significantly affecting the model performance on the remaining data. This topic is becoming increasingly important in protecting user privacy and eliminating harmful or outdated data. The key challenge lies in effectively and efficiently unlearning specific information without compromising the model's utility on the retained data. For pre-trained models, fine-tuning is an important way to achieve the unlearning target. Previous work typically fine-tuned the entire model's parameters, which incurred significant computational costs. In addition, the fine-tuning process may cause shifts in the intermediate layer features, affecting the model's overall utility. In this work, we propose a novel and efficient machine unlearning method for pre-trained models. We term the method Residual Feature Alignment Unlearning. Specifically, we leverage LoRA (Low-Rank Adaptation) to decompose the model's intermediate features into pre-trained features and residual features. By adjusting the residual features, we align the unlearned model with the pre-trained model at the intermediate feature level to achieve both unlearning and remaining targets. The method aims to learn zero residuals on the retained set and shifted residuals on the unlearning set. Extensive experiments on numerous datasets validate the effectiveness of our approach.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑