We consider the problem of iterative machine teaching, where a teacher sequentially provides examples based on the status of a learner under a discrete input space (i.e., a pool of finite samples), which greatly limits the teacher's capability. To address this issue, we study iterative teaching under a continuous input space where the input example (i.e., image) can be either generated by solving an optimization problem or drawn directly from a continuous distribution. Specifically, we propose data hallucination teaching (DHT) where the teacher can generate input data intelligently based on labels, the learner's status and the target concept. We study a number of challenging teaching setups (e.g., linear/neural learners in omniscient and black-box settings). Extensive empirical results verify the effectiveness of DHT.
@article{arxiv.2210.17467,
title = {Iterative Teaching by Data Hallucination},
author = {Zeju Qiu and Weiyang Liu and Tim Z. Xiao and Zhen Liu and Umang Bhatt and Yucen Luo and Adrian Weller and Bernhard Schölkopf},
journal= {arXiv preprint arXiv:2210.17467},
year = {2023}
}