Near-Optimal Machine Teaching via Explanatory Teaching Sets

Yuxin Chen, Oisin Mac Aodha, Shihan Su, Pietro Perona, Yisong Yue

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Modern applications of machine teaching for humans often involve domain-specific, non- trivial target hypothesis classes. To facilitate understanding of the target hypothesis, it is crucial for the teaching algorithm to use examples which are interpretable to the human learner. In this paper, we propose NOTES, a principled framework for constructing interpretable teaching sets, utilizing explanations to accelerate the teaching process. Our algorithm is built upon a natural stochastic model of learners and a novel submodular surrogate objective function which greedily selects interpretable teaching examples. We prove that NOTES is competitive with the optimal explanation-based teaching strategy. We further instantiate NOTES with a specific hypothesis class, which can be viewed as an interpretable approximation of any hypothesis class, allowing us to handle complex hypothesis in practice. We demonstrate the effectiveness of NOTES on several image classification tasks, for both simulated and real human learners. Our experimental results suggest that by leveraging explanations, one can significantly speed up teaching.
Original languageEnglish
Title of host publicationProceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics
EditorsAmos Storkey, Fernando Perez-Cruz
Place of PublicationPlaya Blanca, Lanzarote, Canary Islands
Number of pages9
Publication statusPublished - 1 Sept 2018
EventThe 21st International Conference on Artificial Intelligence and Statistics - Playa Blanca, Lanzarote, Canary Islands, Lanzarote, Spain
Duration: 9 Apr 201811 Apr 2018
Conference number: 21

Publication series

NameProceedings of Machine Learning Research
ISSN (Electronic)2640-3498


ConferenceThe 21st International Conference on Artificial Intelligence and Statistics
Abbreviated titleAISTATS 2018
Internet address


Dive into the research topics of 'Near-Optimal Machine Teaching via Explanatory Teaching Sets'. Together they form a unique fingerprint.

Cite this