Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needs
Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needs
复制标题
DOI：
10.1145/3411764.3445088
复制
发表时间：
2021-01
期刊：
影响因子：
--
通讯作者：
Harini Suresh;Steven R. Gomez;K. Nam;Arvind Satyanarayan
中科院分区：
文献类型：
--
作者：
Harini Suresh;Steven R. Gomez;K. Nam;Arvind Satyanarayan
为了确保问责和减轻损害，重要的是不同的利益相关者可以询问黑盒自动化系统，并找到可理解的、相关的和对他们有用的信息。在本文中，我们避免对可解释性利益相关者进行基于先前专业知识和角色的分类，而是支持一个更细粒度的框架，该框架将利益相关者的知识与他们的可解释性需求分离。我们通过正式的、工具性的和个人的知识以及它如何在机器学习、数据领域和一般环境中表现出来来描述利益相关者。此外，我们还提取了利益相关者需求的分层类型，以区分较高级别的域目标和较低级别的可解释性任务。在评估我们框架的描述性、评估性和生成性的能力时，我们发现我们对利益相关者的更细微的处理揭示了可解释性文献中的差距和机会，增加了用户研究的设计和比较的精确度，并促进了进行这项研究的更反身的方法。
To ensure accountability and mitigate harm, it is critical that diverse stakeholders can interrogate black-box automated systems and find information that is understandable, relevant, and useful to them. In this paper, we eschew prior expertise- and role-based categorizations of interpretability stakeholders in favor of a more granular framework that decouples stakeholders’ knowledge from their interpretability needs. We characterize stakeholders by their formal, instrumental, and personal knowledge and how it manifests in the contexts of machine learning, the data domain, and the general milieu. We additionally distill a hierarchical typology of stakeholder needs that distinguishes higher-level domain goals from lower-level interpretability tasks. In assessing the descriptive, evaluative, and generative powers of our framework, we find our more nuanced treatment of stakeholders reveals gaps and opportunities in the interpretability literature, adds precision to the design and comparison of user studies, and facilitates a more reflexive approach to conducting this research.