arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.08657cs.LGstat.ME
收藏

两阶段数据合成:一种基于统计的隐私与预测之间的受限权衡

Two-Stage Data Synthesization: A Statistics-Driven Restricted Trade-off between Privacy and Prediction

Center for Intelligent Decision-Making and Machine Learning, School of Management, Xi’an Jiaotong University(智能决策与机器学习中心,管理学院,西安交通大学);Department of Mathematics, Hong Kong Baptist University(数学系,香港 Baptist 大学);School of Mathematics and Statistics, University of Sydney(数学与统计学学院,悉尼大学)

Xiaotong Liu, Shao-Bo Lin, Jun Fan, Ding-Xuan Zhou

AI总结:

本文提出了一种两阶段数据合成方法,结合统计学优势,在隐私与预测之间实现受限权衡,通过核岭回归和混合操作提升预测性能。

摘要:

合成数据在各个领域中获得了越来越多的关注,其在下游预测任务中的性能表现也受到越来越多的重视。然而,大多数现有的合成策略侧重于保持统计信息。尽管一些研究针对预测性能保证进行了探讨,但其单阶段合成设计使得在需要显著扰动以满足隐私要求和对这种扰动敏感的预测性能之间难以达到平衡。我们提出了一种两阶段合成策略。在第一阶段,我们引入了一种合成后混合策略,该策略包括生成纯合成数据的合成操作,随后将合成数据与原始数据融合的混合操作。在第二阶段,我们提出了基于核岭回归(KRR)的合成策略,其中首先在原始数据上训练一个KRR模型,然后利用第一阶段生成的合成输入来生成合成输出。通过利用KRR的理论优势和第一阶段实现的协方差分布保留,我们提出的两阶段合成策略实现了基于统计的隐私-预测权衡,并保证了最优的预测性能。我们验证了我们的方法,并通过理论和数值方法展示了其在实现隐私-预测权衡时的统计驱动性和受限性。此外,我们通过营销问题和五个真实世界数据集的应用展示了其通用性。

英文摘要:

Synthetic data have gained increasing attention across various domains, with a growing emphasis on their performance in downstream prediction tasks. However, most existing synthesis strategies focus on maintaining statistical information. Although some studies address prediction performance guarantees, their single-stage synthesis designs make it challenging to balance the privacy requirements that necessitate significant perturbations and the prediction performance that is sensitive to such perturbations. We propose a two-stage synthesis strategy. In the first stage, we introduce a synthesis-then-hybrid strategy, which involves a synthesis operation to generate pure synthetic data, followed by a hybrid operation that fuses the synthetic data with the original data. In the second stage, we present a kernel ridge regression (KRR)-based synthesis strategy, where a KRR model is first trained on the original data and then used to generate synthetic outputs based on the synthetic inputs produced in the first stage. By leveraging the theoretical strengths of KRR and the covariant distribution retention achieved in the first stage, our proposed two-stage synthesis strategy enables a statistics-driven restricted privacy--prediction trade-off and guarantee optimal prediction performance. We validate our approach and demonstrate its characteristics of being statistics-driven and restricted in achieving the privacy--prediction trade-off both theoretically and numerically. Additionally, we showcase its generalizability through applications to a marketing problem and five real-world datasets.

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。

↑