Iterative Machine Teaching

Weiyang Liu, Bo Dai, Ahmad Humayun, Charlene Tay, Chen Yu, Linda B. Smith, James M. Rehg, Le Song
Proceedings of the 34th International Conference on Machine Learning, PMLR 70:2149-2158, 2017.

Abstract

In this paper, we consider the problem of machine teaching, the inverse problem of machine learning. Different from traditional machine teaching which views the learners as batch algorithms, we study a new paradigm where the learner uses an iterative algorithm and a teacher can feed examples sequentially and intelligently based on the current performance of the learner. We show that the teaching complexity in the iterative case is very different from that in the batch case. Instead of constructing a minimal training set for learners, our iterative machine teaching focuses on achieving fast convergence in the learner model. Depending on the level of information the teacher has from the learner model, we design teaching algorithms which can provably reduce the number of teaching examples and achieve faster convergence than learning without teachers. We also validate our theoretical findings with extensive experiments on different data distribution and real image datasets.

Cite this Paper

BibTeX
@InProceedings{pmlr-v70-liu17b, title = {Iterative Machine Teaching}, author = {Weiyang Liu and Bo Dai and Ahmad Humayun and Charlene Tay and Chen Yu and Linda B. Smith and James M. Rehg and Le Song}, booktitle = {Proceedings of the 34th International Conference on Machine Learning}, pages = {2149--2158}, year = {2017}, editor = {Precup, Doina and Teh, Yee Whye}, volume = {70}, series = {Proceedings of Machine Learning Research}, month = {06--11 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v70/liu17b/liu17b.pdf}, url = {https://proceedings.mlr.press/v70/liu17b.html}, abstract = {In this paper, we consider the problem of machine teaching, the inverse problem of machine learning. Different from traditional machine teaching which views the learners as batch algorithms, we study a new paradigm where the learner uses an iterative algorithm and a teacher can feed examples sequentially and intelligently based on the current performance of the learner. We show that the teaching complexity in the iterative case is very different from that in the batch case. Instead of constructing a minimal training set for learners, our iterative machine teaching focuses on achieving fast convergence in the learner model. Depending on the level of information the teacher has from the learner model, we design teaching algorithms which can provably reduce the number of teaching examples and achieve faster convergence than learning without teachers. We also validate our theoretical findings with extensive experiments on different data distribution and real image datasets.} }
Endnote
%0 Conference Paper %T Iterative Machine Teaching %A Weiyang Liu %A Bo Dai %A Ahmad Humayun %A Charlene Tay %A Chen Yu %A Linda B. Smith %A James M. Rehg %A Le Song %B Proceedings of the 34th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2017 %E Doina Precup %E Yee Whye Teh %F pmlr-v70-liu17b %I PMLR %P 2149--2158 %U https://proceedings.mlr.press/v70/liu17b.html %V 70 %X In this paper, we consider the problem of machine teaching, the inverse problem of machine learning. Different from traditional machine teaching which views the learners as batch algorithms, we study a new paradigm where the learner uses an iterative algorithm and a teacher can feed examples sequentially and intelligently based on the current performance of the learner. We show that the teaching complexity in the iterative case is very different from that in the batch case. Instead of constructing a minimal training set for learners, our iterative machine teaching focuses on achieving fast convergence in the learner model. Depending on the level of information the teacher has from the learner model, we design teaching algorithms which can provably reduce the number of teaching examples and achieve faster convergence than learning without teachers. We also validate our theoretical findings with extensive experiments on different data distribution and real image datasets.
APA
Liu, W., Dai, B., Humayun, A., Tay, C., Yu, C., Smith, L.B., Rehg, J.M. & Song, L.. (2017). Iterative Machine Teaching. Proceedings of the 34th International Conference on Machine Learning, in Proceedings of Machine Learning Research 70:2149-2158 Available from https://proceedings.mlr.press/v70/liu17b.html.

Related Material