arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2205.01040cs.LG
收藏

面向深度学习的不确定性工具箱综述

A Survey on Uncertainty Toolkits for Deep Learning

University of Bonn(波恩大学);Fraunhofer IAIS(弗劳恩霍夫智能分析与信息系统研究所)

Maximilian Pintz, Joachim Sicking, Maximilian Poretschkin, Maram Akila

摘要:

深度学习(DL)的成功促进了统一框架(如tensorflow或pytorch)的创建,因为这是由它们的创建所驱动的。具有共同的构建块有助于交换,例如,模型或概念,并使发展更容易复制。尽管如此,对深度学习模型的稳健和可靠的评估和评价往往被证明是具有挑战性的。这与其日益增长的安全相关性不一致,最近在“值得信赖的ML”领域达到了高潮。我们认为,除其他外,进一步统一评价和保障方法的工具包,即,小型和专门的框架衍生物,可能会对可信度和可重复性问题产生积极影响。为此,我们提出了第一个调查工具包的不确定性估计(UE)在DL,UE形成了评估模型可靠性的基石。我们调查了11个工具包的建模和评估功能,提供了三个最有前途的深入比较,即Pyro,Tensorflow概率和不确定性量化360。前两个框架提供了很大程度的灵活性和与各自框架的无缝集成,最后一个框架的方法范围更大。

英文摘要:

The success of deep learning (DL) fostered the creation of unifying frameworks such as tensorflow or pytorch as much as it was driven by their creation in return. Having common building blocks facilitates the exchange of, e.g., models or concepts and makes developments easier replicable. Nonetheless, robust and reliable evaluation and assessment of DL models has often proven challenging. This is at odds with their increasing safety relevance, which recently culminated in the field of "trustworthy ML". We believe that, among others, further unification of evaluation and safeguarding methodologies in terms of toolkits, i.e., small and specialized framework derivatives, might positively impact problems of trustworthiness as well as reproducibility. To this end, we present the first survey on toolkits for uncertainty estimation (UE) in DL, as UE forms a cornerstone in assessing model reliability. We investigate 11 toolkits with respect to modeling and evaluation capabilities, providing an in-depth comparison for the three most promising ones, namely Pyro, Tensorflow Probability, and Uncertainty Quantification 360. While the first two provide a large degree of flexibility and seamless integration into their respective framework, the last one has the larger methodological scope.

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。

↑