Model-Agnostic Interpretability of Machine Learning

TLDR

Interpretability is increasingly vital in machine learning, as transparent models can match or exceed non‑interpretable ones in accuracy and are preferred when trust and usability are paramount, yet limiting models to interpretable ones can severely constrain performance. The paper advocates explaining predictions with model‑agnostic methods. The authors outline challenges for model‑agnostic explanations and review LIME, a recent approach that tackles these issues. Treating models as black‑box functions, model‑agnostic explanations offer flexibility in model choice, explanation, and representation, enhancing debugging, comparison, and user interfaces.

Abstract

Understanding why machine learning models behave the way they do empowers both system designers and end-users in many ways: in model selection, feature engineering, in order to trust and act upon the predictions, and in more intuitive user interfaces. Thus, interpretability has become a vital concern in machine learning, and work in the area of interpretable models has found renewed interest. In some applications, such models are as accurate as non-interpretable ones, and thus are preferred for their transparency. Even when they are not accurate, they may still be preferred when interpretability is of paramount importance. However, restricting machine learning to interpretable models is often a severe limitation. In this paper we argue for explaining machine learning predictions using model-agnostic approaches. By treating the machine learning models as black-box functions, these approaches provide crucial flexibility in the choice of models, explanations, and representations, improving debugging, comparison, and interfaces for a variety of users and models. We also outline the main challenges for such methods, and review a recently-introduced model-agnostic explanation approach (LIME) that addresses these challenges.