arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.13181cs.LG
收藏

生成模型中的数据挖掘:一个形式化框架

Data-Copying in Generative Models: A Formal Framework

University of California, San Diego(加州大学圣地亚哥分校)

Robi Bhattacharjee, Sanjoy Dasgupta, Kamalika Chaudhuri

摘要:

最近,人们对通过深度神经网络检测和解决训练数据的记忆感兴趣。Meehan等人提出了一个生成模型中的记忆框架,称为“数据复制”。等(2020)。我们以他们的工作为基础,证明他们的框架可能无法检测某些类型的公然记忆。受此启发和非参数方法的理论,我们提供了一个替代定义的数据复制,适用于更多的本地。我们提供了一种方法来检测数据复制,并证明了它的作品具有很高的概率时,有足够的数据。我们还提供了下限,表征可靠检测的样本要求。

英文摘要:

There has been some recent interest in detecting and addressing memorization of training data by deep neural networks. A formal framework for memorization in generative models, called "data-copying," was proposed by Meehan et. al. (2020). We build upon their work to show that their framework may fail to detect certain kinds of blatant memorization. Motivated by this and the theory of non-parametric methods, we provide an alternative definition of data-copying that applies more locally. We provide a method to detect data-copying, and provably show that it works with high probability when enough data is available. We also provide lower bounds that characterize the sample requirement for reliable detection.

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。

↑