Iterative Teaching by Data Hallucination

Zeju Qiu, Weiyang Liu, Tim Z. Xiao, Zhen Liu, Umang Bhatt, Yucen Luo, Adrian Weller, Bernhard Schölkopf
Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, PMLR 206:9892-9913, 2023.

Abstract

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.

Cite this Paper


BibTeX
@InProceedings{pmlr-v206-qiu23a, title = {Iterative Teaching by Data Hallucination}, author = {Qiu, Zeju and Liu, Weiyang and Xiao, Tim Z. and Liu, Zhen and Bhatt, Umang and Luo, Yucen and Weller, Adrian and Sch\"olkopf, Bernhard}, booktitle = {Proceedings of The 26th International Conference on Artificial Intelligence and Statistics}, pages = {9892--9913}, year = {2023}, editor = {Ruiz, Francisco and Dy, Jennifer and van de Meent, Jan-Willem}, volume = {206}, series = {Proceedings of Machine Learning Research}, month = {25--27 Apr}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v206/qiu23a/qiu23a.pdf}, url = {https://proceedings.mlr.press/v206/qiu23a.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T Iterative Teaching by Data Hallucination %A Zeju Qiu %A Weiyang Liu %A Tim Z. Xiao %A Zhen Liu %A Umang Bhatt %A Yucen Luo %A Adrian Weller %A Bernhard Schölkopf %B Proceedings of The 26th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2023 %E Francisco Ruiz %E Jennifer Dy %E Jan-Willem van de Meent %F pmlr-v206-qiu23a %I PMLR %P 9892--9913 %U https://proceedings.mlr.press/v206/qiu23a.html %V 206 %X 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.
APA
Qiu, Z., Liu, W., Xiao, T.Z., Liu, Z., Bhatt, U., Luo, Y., Weller, A. & Schölkopf, B.. (2023). Iterative Teaching by Data Hallucination. Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 206:9892-9913 Available from https://proceedings.mlr.press/v206/qiu23a.html.

Related Material