Skip to yearly menu bar Skip to main content


Iterative Teaching by Data Hallucination

Zeju Qiu · Weiyang Liu · Tim Xiao · Zhen Liu · Umang Bhatt · Yucen Luo · Adrian Weller · Bernhard Schölkopf

Auditorium 1 Foyer 52


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.

Live content is unavailable. Log in and register to view live content