论文标题
公共资源的私人领域改编
Private Domain Adaptation from a Public Source
论文作者
论文摘要
在各种应用程序中，一个关键问题是从公共源域进行适应的域适应性，对于该域而没有隐私限制的相对较大的标记数据，可以供您使用，而不是一个私人目标域，为此，私人样本几乎没有或没有标记的数据。在对源或目标数据没有隐私限制的回归问题中，基于几种理论保证的差异最小化算法被证明超过了许多其他适应性算法基础。在这种方法的基础上，我们设计了基于私有差异的算法，以适应带有公共标记的数据到具有未标记的私人数据的目标域的源域。我们对私人算法的设计和分析非常关键地取决于我们证明的几个关键属性，以平稳地近似加权差异，例如它相对于$ \ ell_1 $ norm的平滑度及其梯度的灵敏度。我们的解决方案基于Frank-Wolfe和Mirror-Despent算法的私人变体。我们表明，我们的适应算法受益于强有力的概括和隐私保证，并报告了证明其有效性的实验结果。
A key problem in a variety of applications is that of domain adaptation from a public source domain, for which a relatively large amount of labeled data with no privacy constraints is at one's disposal, to a private target domain, for which a private sample is available with very few or no labeled data. In regression problems with no privacy constraints on the source or target data, a discrepancy minimization algorithm based on several theoretical guarantees was shown to outperform a number of other adaptation algorithm baselines. Building on that approach, we design differentially private discrepancy-based algorithms for adaptation from a source domain with public labeled data to a target domain with unlabeled private data. The design and analysis of our private algorithms critically hinge upon several key properties we prove for a smooth approximation of the weighted discrepancy, such as its smoothness with respect to the $\ell_1$-norm and the sensitivity of its gradient. Our solutions are based on private variants of Frank-Wolfe and Mirror-Descent algorithms. We show that our adaptation algorithms benefit from strong generalization and privacy guarantees and report the results of experiments demonstrating their effectiveness.
