[论文解读] Mediation Challenges and Socio-Technical Gaps for Explainable Deep Learning Applications

Rafael Brandão, Joel Luís Carbonera+4 more|arXiv (Cornell University)|Jul 16, 2019

Explainable Artificial Intelligence (XAI)参考文献 50被引用 4

一句话总结

本文识别出深度学习模型中嵌入的技术含义与用户赋予的社会含义之间存在关键性的社会-技术鸿沟，提出三项'可解释人工智能调解挑战'以弥合这一差距。通过与工业研发实验室中的深度学习专家开展质性案例研究，发现从业者缺乏内在动力去考虑其工作的社会影响，因此必须借助中介者和跨学科合作，以满足监管和公众对可解释性的要求。

ABSTRACT

The presumed data owners' right to explanations brought about by the General Data Protection Regulation in Europe has shed light on the social challenges of explainable artificial intelligence (XAI). In this paper, we present a case study with Deep Learning (DL) experts from a research and development laboratory focused on the delivery of industrial-strength AI technologies. Our aim was to investigate the social meaning (i.e. meaning to others) that DL experts assign to what they do, given a richly contextualized and familiar domain of application. Using qualitative research techniques to collect and analyze empirical data, our study has shown that participating DL experts did not spontaneously engage into considerations about the social meaning of machine learning models that they build. Moreover, when explicitly stimulated to do so, these experts expressed expectations that, with real-world DL application, there will be available mediators to bridge the gap between technical meanings that drive DL work, and social meanings that AI technology users assign to it. We concluded that current research incentives and values guiding the participants' scientific interests and conduct are at odds with those required to face some of the scientific challenges involved in advancing XAI, and thus responding to the alleged data owners' right to explanations or similar societal demands emerging from current debates. As a concrete contribution to mitigate what seems to be a more general problem, we propose three preliminary XAI Mediation Challenges with the potential to bring together technical and social meanings of DL applications, as well as to foster much needed interdisciplinary collaboration among AI and the Social Sciences researchers.

研究动机与目标

• 调查深度学习专家在现实情境中如何理解其模型的社会含义。
• 识别技术开发实践与社会对可解释性期望之间的脱节。
• 应对深度学习专家缺乏内在动力去考虑其工作社会影响的问题。
• 提出具体调解挑战，以促进人工智能与社会科学研究人员之间的协作。
• 通过协调技术与社会含义，回应如GDPR中规定的解释权等监管要求。

提出的方法

• 在一家工业研发实验室中对12名深度学习专家开展质性案例研究。
• 采用半结构化访谈与主题分析，探究专家对可解释性和社会含义的理解。
• 在初步非自发性参与后，通过有针对性的问题激发其对社会影响的反思。
• 识别出技术工作流程中缺乏社会考量的重复性主题。
• 提出三项XAI调解挑战，以在人工智能开发中整合技术和社交含义。
• 倡导人工智能研究人员与社会科学家之间开展跨学科合作，以弥合社会-技术鸿沟。

实验结果

研究问题

• RQ1 深度学习专家如何在工业情境中为其所开发的模型赋予社会含义？
• RQ2 为何尽管面临监管和社会要求，深度学习专家仍未能自发考虑其模型的社会影响？
• RQ3 需要何种中介者或协作框架，以弥合人工智能系统中技术与社会含义之间的差距？
• RQ4 当前深度学习研究激励机制与价值观如何与可解释人工智能的目标产生冲突？
• RQ5 哪些具体挑战能够促进人工智能与社会科学研究人员之间的跨学科合作？

主要发现

• 深度学习专家在真实应用场景下也未自发考虑其模型的社会含义。
• 在被明确提示后，专家表达了对中介者在协调技术与社会含义方面发挥重要作用的强烈期望。
• 当前深度学习研究的激励机制与价值观与推动可解释人工智能的需求不一致。
• 本研究识别出深度学习开发的技术焦点与社会对可解释性需求之间存在根本性的社会-技术鸿沟。
• 提出三项XAI调解挑战，作为整合人工智能应用中技术和社交维度的具体路径。
• 研究结果凸显了迫切需要跨学科合作，以满足监管和伦理对人工智能透明度的要求。