Explainability fact sheets
Explainability fact sheets
复制标题
可解释性情况说明书
DOI：
10.1145/3351095.3372870
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Sokol K
中科院分区：
文献类型：
--
作者：
Sokol K
机器学习中的解释有多种形式，但关于它们所需属性的共识尚未出现。在本文中，我们介绍了一个分类和一组描述符，它们可以用来描述和系统地评估五个关键维度上的可解释系统：功能性、可操作性、可用性、安全性和有效性。为了设计一个全面和具有代表性的分类和相关描述符，我们调查了可解释的人工智能文献，提取了其他作者在他们的研究中提出或隐含使用的标准和期望数据。调查包括介绍新的可解释性算法的论文，以了解使用什么标准来指导它们的开发以及如何评估这些算法，以及从计算机科学和社会科学的角度提出此类标准的论文。这一新颖的框架允许系统地比较和对比可解释性方法，不仅可以更好地了解它们的能力，而且还可以确定它们的理论质量和实现特性之间的差异。我们以可解释性情况说明书的形式开发了框架的可操作性，这使研究人员和实践者都能够快速掌握特定可解释方法的能力和限制。当用作工作表时，我们的分类可以通过帮助它们沿着五个提议的维度进行批判性评估来指导新的可解释性方法的开发。
Explanations in Machine Learning come in many forms, but a consensus regarding their desired properties is yet to emerge. In this paper we introduce a taxonomy and a set of descriptors that can be used to characterise and systematically assess explainable systems along five key dimensions: functional, operational, usability, safety and validation. In order to design a comprehensive and representative taxonomy and associated descriptors we surveyed the eXplainable Artificial Intelligence literature, extracting the criteria and desiderata that other authors have proposed or implicitly used in their research. The survey includes papers introducing new explainability algorithms to see what criteria are used to guide their development and how these algorithms are evaluated, as well as papers proposing such criteria from both computer science and social science perspectives. This novel framework allows to systematically compare and contrast explainability approaches, not just to better understand their capabilities but also to identify discrepancies between their theoretical qualities and properties of their implementations. We developed an operationalisation of the framework in the form ofExplainability Fact Sheets, which enable researchers and practitioners alike to quickly grasp capabilities and limitations of a particular explainable method. When used as aWork Sheet, our taxonomy can guide the development of new explainability approaches by aiding in their critical evaluation along the five proposed dimensions.