Measuring the Quality of Explanations: The System Causability Scale (SCS) Comparing Human and Machine Explanations
Measuring the Quality of Explanations: The System Causability Scale (SCS) Comparing Human and Machine Explanations
复制标题
DOI：
10.1007/s13218-020-00636-z
复制
发表时间：
2020-06-01
影响因子：
2.9
通讯作者：
Mueller, Heimo
中科院分区：
文献类型：
--
作者：
Holzinger, Andreas;Carrington, Andre;Mueller, Heimo
最近在人工智能（AI）和机器学习（ML）方面的成功允许在没有任何人为干预的情况下自动解决问题。自主方法可能非常方便。然而，在某些领域，例如，在医学领域中，有必要使领域专家能够理解为什么算法得出某个结果。因此，可解释人工智能（xAI）领域迅速在全球各个领域，特别是医学领域引起了人们的兴趣。可解释AI研究不透明AI/ML的透明度和可追溯性，并且已经有各种各样的方法。例如，利用逐层相关性传播，可以突出显示导致结果的神经网络的输入的相关部分和神经网络中的表示。这是确保最终用户，例如，医疗专业人员，负责AI/ML的决策，并对专业人员和监管机构感兴趣。交互式ML将人类专业知识的组成部分添加到AI/ML过程中，使他们能够重新制定和追溯AI/ML结果，例如让他们检查其可扩展性。这需要新的人机界面来实现可解释的AI。为了构建有效且高效的交互式人机界面，我们必须处理如何评估可解释人工智能系统给出的解释质量的问题。在本文中，我们介绍了我们的系统因果性量表来衡量解释的质量。它基于我们的因果性概念（Holzinger et al. in Wiley Intercept Rev Data Min Knowl Discov 9（4），2019），结合了从广泛接受的可用性量表改编的概念。
Recent success in Artificial Intelligence (AI) and Machine Learning (ML) allow problem solving automatically without any human intervention. Autonomous approaches can be very convenient. However, in certain domains, e.g., in the medical domain, it is necessary to enable a domain expert to understand, why an algorithm came up with a certain result. Consequently, the field of Explainable AI (xAI) rapidly gained interest worldwide in various domains, particularly in medicine. Explainable AI studies transparency and traceability of opaque AI/ML and there are already a huge variety of methods. For example with layer-wise relevance propagation relevant parts of inputs to, and representations in, a neural network which caused a result, can be highlighted. This is a first important step to ensure that end users, e.g., medical professionals, assume responsibility for decision making with AI/ML and of interest to professionals and regulators. Interactive ML adds the component of human expertise to AI/ML processes by enabling them to re-enact and retrace AI/ML results, e.g. let them check it for plausibility. This requires new human-AI interfaces for explainable AI. In order to build effective and efficient interactive human-AI interfaces we have to deal with the question of how to evaluate the quality of explanations given by an explainable AI system. In this paper we introduce our System Causability Scale to measure the quality of explanations. It is based on our notion of Causability (Holzinger et al. in Wiley Interdiscip Rev Data Min Knowl Discov 9(4), 2019) combined with concepts adapted from a widely-accepted usability scale.