The Doctor Just Won't Accept That!
This work addresses the foundational problem of defining clear goals for interpretable machine learning to advance the field beyond incremental progress.
The paper critiques the justification for interpretable machine learning, arguing that vague claims about stakeholder acceptance are insufficient and that the field must precisely define what stakeholders need and whether those needs are reasonable and feasible.
Calls to arms to build interpretable models express a well-founded discomfort with machine learning. Should a software agent that does not even know what a loan is decide who qualifies for one? Indeed, we ought to be cautious about injecting machine learning (or anything else, for that matter) into applications where there may be a significant risk of causing social harm. However, claims that stakeholders "just won't accept that!" do not provide a sufficient foundation for a proposed field of study. For the field of interpretable machine learning to advance, we must ask the following questions: What precisely won't various stakeholders accept? What do they want? Are these desiderata reasonable? Are they feasible? In order to answer these questions, we'll have to give real-world problems and their respective stakeholders greater consideration.