Examples are not enough, learn to criticize! Criticism for Interpretability

TLDR

Example‑based explanations are widely used to improve interpretability of complex distributions, yet prototypes alone rarely capture the full complexity. The study aims to enhance users’ mental models of complex data distributions by adding criticism to prototype explanations. Using a Bayesian model‑criticism framework, the authors develop MMD‑critic, an algorithm that efficiently learns prototypes and complementary criticism to aid human interpretability. A pilot study shows that MMD‑critic’s prototypes and criticism improve human understanding, and its prototypes achieve competitive classification performance against baselines.

Abstract

Example-based explanations are widely used in the effort to improve the interpretability of highly complex distributions. However, prototypes alone are rarely sufficient to represent the gist of the complexity. In order for users to construct better mental models and understand complex data distributions, we also need {\em criticism} to explain what are \textit{not} captured by prototypes. Motivated by the Bayesian model criticism framework, we develop \texttt{MMD-critic} which efficiently learns prototypes and criticism, designed to aid human interpretability. A human subject pilot study shows that the \texttt{MMD-critic} selects prototypes and criticism that are useful to facilitate human understanding and reasoning. We also evaluate the prototypes selected by \texttt{MMD-critic} via a nearest prototype classifier, showing competitive performance compared to baselines.