Iterative Teaching by Label Synthesis
This addresses the challenge of efficient teaching in machine learning, though it appears incremental as it builds on existing iterative teaching methods.
The paper tackles the problem of iterative machine teaching by proposing a label synthesis framework that randomly selects input examples and synthesizes outputs, avoiding costly example selection while achieving exponential teachability.
In this paper, we consider the problem of iterative machine teaching, where a teacher provides examples sequentially based on the current iterative learner. In contrast to previous methods that have to scan over the entire pool and select teaching examples from it in each iteration, we propose a label synthesis teaching framework where the teacher randomly selects input teaching examples (e.g., images) and then synthesizes suitable outputs (e.g., labels) for them. We show that this framework can avoid costly example selection while still provably achieving exponential teachability. We propose multiple novel teaching algorithms in this framework. Finally, we empirically demonstrate the value of our framework.