Rethinking Explainable Machine Learning as Applied Statistics
This perspective aims to improve research practices in explainable ML by emphasizing interpretation, addressing a foundational issue for researchers and practitioners.
The authors argue that explainable machine learning should be viewed through the lens of applied statistics, framing explanations as statistics of high-dimensional functions to address unclear goals and usage in current research.
In the rapidly growing literature on explanation algorithms, it often remains unclear what precisely these algorithms are for and how they should be used. In this position paper, we argue for a novel and pragmatic perspective: Explainable machine learning needs to recognize its parallels with applied statistics. Concretely, explanations are statistics of high-dimensional functions, and we should think about them analogously to traditional statistical quantities. Among others, this implies that we must think carefully about the matter of interpretation, or how the explanations relate to intuitive questions that humans have about the world. The fact that this is scarcely being discussed in research papers is one of the main drawbacks of the current literature. Moving forward, the analogy between explainable machine learning and applied statistics suggests fruitful ways for how research practices can be improved.