arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.08196cs.LG
收藏

深度回归遗忘

Deep Regression Unlearning

Mavvex Labs(Mavvex实验室);Kalinga Institute of Industrial Technology(卡林加工业技术学院);National University of Singapore(新加坡国立大学)

Ayush K Tarun, Vikram S Chundawat, Murari Mandal, Mohan Kankanhalli

AI总结:

本文针对深度回归模型遗忘问题,提出 Blindspot 权重优化方法和高斯微调方法,并适配回归遗忘指标,在视觉、语言和预测任务上验证了其有效性。

摘要:

随着数据保护与隐私法规的出台,按需从机器学习模型中移除数据来源变得至关重要。过去几年中,机器学习遗忘在高效且有效地从机器学习模型中删除某些训练数据信息方面取得了显著进展。本文探索回归问题中的遗忘,尤其是深度学习模型中的遗忘。分类和简单线性回归中的遗忘已得到较多研究,但深度回归模型中的遗忘至今仍基本是一个未被触及的问题。本文提出了泛化良好且对隐私攻击具有鲁棒性的深度回归遗忘方法。我们提出了 Blindspot 遗忘方法,该方法采用一种新颖的权重优化过程:使用一个随机初始化的模型(部分接触保留样本)和原始模型的副本,共同选择性地印记我们希望保留的数据知识,并清除我们希望遗忘的数据信息。我们还提出了一种用于回归遗忘的高斯微调方法。现有的分类遗忘指标不能直接适用于回归遗忘,因此我们针对回归场景对这些指标进行了适配。我们在计算机视觉、自然语言处理和预测应用中进行了回归遗忘实验。我们的方法在所有数据集和所有指标上均表现出优异的性能。源代码:https://github.com/ayu987/deep-regression-unlearning

英文摘要:

With the introduction of data protection and privacy regulations, it has become crucial to remove the lineage of data on demand from a machine learning (ML) model. In the last few years, there have been notable developments in machine unlearning to remove the information of certain training data efficiently and effectively from ML models. In this work, we explore unlearning for the regression problem, particularly in deep learning models. Unlearning in classification and simple linear regression has been considerably investigated. However, unlearning in deep regression models largely remains an untouched problem till now. In this work, we introduce deep regression unlearning methods that generalize well and are robust to privacy attacks. We propose the Blindspot unlearning method which uses a novel weight optimization process. A randomly initialized model, partially exposed to the retain samples and a copy of the original model are used together to selectively imprint knowledge about the data that we wish to keep and scrub off the information of the data we wish to forget. We also propose a Gaussian fine tuning method for regression unlearning. The existing unlearning metrics for classification are not directly applicable to regression unlearning. Therefore, we adapt these metrics for the regression setting. We conduct regression unlearning experiments for computer vision, natural language processing and forecasting applications. Our methods show excellent performance for all these datasets across all the metrics. Source code: https://github.com/ayu987/deep-regression-unlearning

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。

↑