Iterative Teaching by Label Synthesis

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.

Authors

• Weiyang Liu
• Zhen Liu University of Electronic Science and Technology of China Megvii Technology
• Hanchen Wang
• Liam Paull Mila - Quebec AI Institute Université de Montréal
• Bernhard Schölkopf
• Adrian Weller The Alan Turing Institute University of Cambridge

Keywords

No keywords are indexed for this paper.