Understanding the Role of Adaptivity in Machine Teaching: The Case of Version Space Learners

In real-world applications of education and human teaching, an effective teacher chooses the next example intelligently based on the learner’s current state. However, most of the existing works in algorithmic machine teaching focus on the batch setting, where adaptivity plays no role. In this paper, we study the case of teaching consistent, version space learners in an interactive setting—at any time step, the teacher provides an example, the learner performs an update, and the teacher observes the learner’s new state. We highlight that adaptivity does not speed up the teaching process when considering existing models of version space learners, such as the “worst-case” model (the learner picks the next hypothesis randomly from the version space) and “preference-based” model (the learner picks hypothesis according to some global preference). Inspired by human teaching, we propose a new model where the learner picks hypothesis according to some local preference defined by the current hypothesis. We show that our model exhibits several desirable properties, e.g., adaptivity plays a key role, and the learner’s transitions over hypotheses are smooth/interpretable. We develop efficient teaching algorithms for our model, and demonstrate our results via simulations as well as user studies.