Interpretable and Pedagogical Examples

Smitha Milli, Pieter Abbeel, Igor Mordatch

Abstract: Teachers intentionally pick the most informative examples to show their students. However, if the teacher and student are neural networks, the examples that the teacher network learns to give, although effective at teaching the student, are typically uninterpretable. We show that training the student and teacher iteratively, rather than jointly, can produce interpretable teaching strategies. We evaluate interpretability by (1) measuring the similarity of the teacher's emergent strategies to intuitive strategies in each domain and (2) conducting human experiments to evaluate how effective the teacher's strategies are at teaching humans. We show that the teacher network learns to select or generate interpretable, pedagogical examples to teach rule-based, probabilistic, boolean, and hierarchical concepts.

TL;DR: We show that training a student and teacher network iteratively, rather than jointly, can produce emergent, interpretable teaching strategies.

Keywords: machine teaching, interpretability, communication, cognitive science