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

TL;DR

This paper investigates the impact of adaptivity in machine teaching for version space learners, introducing a new local preference model that highlights the importance of adaptivity and demonstrates its benefits through algorithms and empirical studies.

Contribution

The paper introduces a novel local preference-based model for version space learners, emphasizing the significance of adaptivity in interactive teaching settings.

Findings

Adaptivity significantly improves teaching efficiency in the proposed model.

The new model produces smooth and interpretable hypothesis transitions.

Algorithms based on the model outperform non-adaptive approaches in simulations and user studies.

Abstract

In real-world applications of education, an effective teacher adaptively chooses the next example to teach based on the learner's current state. However, most existing work in algorithmic machine teaching focuses 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 "worst-case" (the learner picks the next hypothesis randomly from the version space) and "preference-based" (the learner picks hypothesis according to some global preference). Inspired by human teaching, we propose a new model where the learner picks hypotheses 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 and demonstrate our results via simulation and user studies.