arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.09680cs.LGcs.CR
收藏

通过可解释提升的准确性、可解释性和差分隐私

Accuracy, Interpretability, and Differential Privacy via Explainable Boosting

Microsoft(微软);University of Pennsylvania(宾夕法尼亚大学);Stanford University(斯坦福大学)

Harsha Nori, Rich Caruana, Zhiqi Bu, Judy Hanwen Shen, Janardhan Kulkarni

摘要:

我们表明,将差分隐私添加到可解释的提升机(EBM)中,这是一种最近用于训练可解释的ML模型的方法,在保护隐私的同时获得了最先进的准确性。我们在多个分类和回归数据集上的实验表明,DP-EBM模型即使有很强的差分隐私保证,也几乎没有准确性损失。除了高准确性之外,将DP应用于EBM的另外两个好处是:a)训练的模型提供精确的全局和局部可解释性,这在需要差分隐私的设置中通常是重要的;以及b)模型可以在训练之后被编辑而不损失隐私以校正DP噪声可能引入的错误。

英文摘要:

We show that adding differential privacy to Explainable Boosting Machines (EBMs), a recent method for training interpretable ML models, yields state-of-the-art accuracy while protecting privacy. Our experiments on multiple classification and regression datasets show that DP-EBM models suffer surprisingly little accuracy loss even with strong differential privacy guarantees. In addition to high accuracy, two other benefits of applying DP to EBMs are: a) trained models provide exact global and local interpretability, which is often important in settings where differential privacy is needed; and b) the models can be edited after training without loss of privacy to correct errors which DP noise may have introduced.

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。

↑