Timezone: »

 
Oral
Examples are not enough, learn to criticize! Criticism for Interpretability
Been Kim · Sanmi Koyejo · Rajiv Khanna

Thu Dec 08 02:30 AM -- 02:50 AM (PST) @ Area 1 + 2
in Interpretable Models »

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.

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

Author Information

Been Kim (Google DeepMind)
Sanmi Koyejo (UIUC)
Sanmi Koyejo

Sanmi Koyejo an Assistant Professor in the Department of Computer Science at Stanford University. Koyejo also spends time at Google as a part of the Brain team. Koyejo's research interests are in developing the principles and practice of trustworthy machine learning. Additionally, Koyejo focuses on applications to neuroscience and healthcare. Koyejo has been the recipient of several awards, including a best paper award from the conference on uncertainty in artificial intelligence (UAI), a Skip Ellis Early Career Award, and a Sloan Fellowship. Koyejo serves as the president of the Black in AI organization.

Rajiv Khanna (UT Austin)

More from the Same Authors