arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.11204cs.LGcs.CRstat.ML
收藏

具有逐项梯度聚集的差分私有变分自编码器

Differentially Private Variational Autoencoders with Term-wise Gradient Aggregation

LINE Corporation(LINE公司);Kyoto University(京都大学);SOKENDAI(综合研究大学院大学)

Tsubasa Takahashi, Shun Takagi, Hajime Ono, Tatsuya Komatsu

摘要:

本文研究了在差分隐私约束下,如何学习具有多种发散性的变分自编码器。我们通常使用适当的先验分布来构建VAE,以描述所学习的表示的期望属性,并引入发散作为正则化项,以使表示接近先验。使用差分私有SGD(DP-SGD),通过注入根据梯度敏感度设计的专用噪声来随机化随机梯度,我们可以轻松构建差分私有模型。然而,我们发现,附加几个分歧增加的灵敏度从O(1)到O(B)的批量大小B。这导致注入大量的噪音,使其难以学习。为了解决上述问题,我们提出了逐项DP-SGD,其以两种不同的方式根据损失项的组成来定制随机梯度。即使在附加散度时,逐项DP-SGD也将灵敏度保持在O(1)。因此,我们可以减少噪音。在我们的实验中,我们证明了我们的方法可以很好地与两对先验分布和发散。

英文摘要:

This paper studies how to learn variational autoencoders with a variety of divergences under differential privacy constraints. We often build a VAE with an appropriate prior distribution to describe the desired properties of the learned representations and introduce a divergence as a regularization term to close the representations to the prior. Using differentially private SGD (DP-SGD), which randomizes a stochastic gradient by injecting a dedicated noise designed according to the gradient's sensitivity, we can easily build a differentially private model. However, we reveal that attaching several divergences increase the sensitivity from O(1) to O(B) in terms of batch size B. That results in injecting a vast amount of noise that makes it hard to learn. To solve the above issue, we propose term-wise DP-SGD that crafts randomized gradients in two different ways tailored to the compositions of the loss terms. The term-wise DP-SGD keeps the sensitivity at O(1) even when attaching the divergence. We can therefore reduce the amount of noise. In our experiments, we demonstrate that our method works well with two pairs of the prior distribution and the divergence.

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。

↑