Skip to yearly menu bar Skip to main content


Poster

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

Been Kim · Sanmi Koyejo · Rajiv Khanna

Area 5+6+7+8 #197

Keywords: [ Combinatorial Optimization ] [ (Other) Applications ] [ (Other) Machine Learning Topics ] [ (Other) Cognitive Science ] [ (Application) Privacy, Anonymity, and Security ]


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.

Live content is unavailable. Log in and register to view live content