Student-Teacher Curriculum Learning via Reinforcement Learning: Predicting Hospital Inpatient Admission Location

Rasheed El-Bouri, David Eyre, Peter Watkinson, Tingting Zhu, David Clifton
Proceedings of the 37th International Conference on Machine Learning, PMLR 119:2848-2857, 2020.

Abstract

Accurate and reliable prediction of hospital admission location is important due to resource-constraints and space availability in a clinical setting, particularly when dealing with patients who come from the emergency department. In this work we propose a student-teacher network via reinforcement learning to deal with this specific problem. A representation of the weights of the student network is treated as the state and is fed as an input to the teacher network. The teacher network’s action is to select the most appropriate batch of data to train the student network on from a training set sorted according to entropy. By validating on three datasets, not only do we show that our approach outperforms state-of-the-art methods on tabular data and performs competitively on image recognition, but also that novel curricula are learned by the teacher network. We demonstrate experimentally that the teacher network can actively learn about the student network and guide it to achieve better performance than if trained alone.

Cite this Paper


BibTeX
@InProceedings{pmlr-v119-el-bouri20a, title = {Student-Teacher Curriculum Learning via Reinforcement Learning: Predicting Hospital Inpatient Admission Location}, author = {El-Bouri, Rasheed and Eyre, David and Watkinson, Peter and Zhu, Tingting and Clifton, David}, booktitle = {Proceedings of the 37th International Conference on Machine Learning}, pages = {2848--2857}, year = {2020}, editor = {III, Hal Daumé and Singh, Aarti}, volume = {119}, series = {Proceedings of Machine Learning Research}, month = {13--18 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v119/el-bouri20a/el-bouri20a.pdf}, url = {https://proceedings.mlr.press/v119/el-bouri20a.html}, abstract = {Accurate and reliable prediction of hospital admission location is important due to resource-constraints and space availability in a clinical setting, particularly when dealing with patients who come from the emergency department. In this work we propose a student-teacher network via reinforcement learning to deal with this specific problem. A representation of the weights of the student network is treated as the state and is fed as an input to the teacher network. The teacher network’s action is to select the most appropriate batch of data to train the student network on from a training set sorted according to entropy. By validating on three datasets, not only do we show that our approach outperforms state-of-the-art methods on tabular data and performs competitively on image recognition, but also that novel curricula are learned by the teacher network. We demonstrate experimentally that the teacher network can actively learn about the student network and guide it to achieve better performance than if trained alone.} }
Endnote
%0 Conference Paper %T Student-Teacher Curriculum Learning via Reinforcement Learning: Predicting Hospital Inpatient Admission Location %A Rasheed El-Bouri %A David Eyre %A Peter Watkinson %A Tingting Zhu %A David Clifton %B Proceedings of the 37th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2020 %E Hal Daumé III %E Aarti Singh %F pmlr-v119-el-bouri20a %I PMLR %P 2848--2857 %U https://proceedings.mlr.press/v119/el-bouri20a.html %V 119 %X Accurate and reliable prediction of hospital admission location is important due to resource-constraints and space availability in a clinical setting, particularly when dealing with patients who come from the emergency department. In this work we propose a student-teacher network via reinforcement learning to deal with this specific problem. A representation of the weights of the student network is treated as the state and is fed as an input to the teacher network. The teacher network’s action is to select the most appropriate batch of data to train the student network on from a training set sorted according to entropy. By validating on three datasets, not only do we show that our approach outperforms state-of-the-art methods on tabular data and performs competitively on image recognition, but also that novel curricula are learned by the teacher network. We demonstrate experimentally that the teacher network can actively learn about the student network and guide it to achieve better performance than if trained alone.
APA
El-Bouri, R., Eyre, D., Watkinson, P., Zhu, T. & Clifton, D.. (2020). Student-Teacher Curriculum Learning via Reinforcement Learning: Predicting Hospital Inpatient Admission Location. Proceedings of the 37th International Conference on Machine Learning, in Proceedings of Machine Learning Research 119:2848-2857 Available from https://proceedings.mlr.press/v119/el-bouri20a.html.

Related Material