CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patients

Dani Kiyasseh, Tingting Zhu, David A Clifton
Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5606-5615, 2021.

Abstract

The healthcare industry generates troves of unlabelled physiological data. This data can be exploited via contrastive learning, a self-supervised pre-training method that encourages representations of instances to be similar to one another. We propose a family of contrastive learning methods, CLOCS, that encourages representations across space, time, \textit{and} patients to be similar to one another. We show that CLOCS consistently outperforms the state-of-the-art methods, BYOL and SimCLR, when performing a linear evaluation of, and fine-tuning on, downstream tasks. We also show that CLOCS achieves strong generalization performance with only 25% of labelled training data. Furthermore, our training procedure naturally generates patient-specific representations that can be used to quantify patient-similarity.

Cite this Paper

BibTeX
@InProceedings{pmlr-v139-kiyasseh21a, title = {CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patients}, author = {Kiyasseh, Dani and Zhu, Tingting and Clifton, David A}, booktitle = {Proceedings of the 38th International Conference on Machine Learning}, pages = {5606--5615}, year = {2021}, editor = {Meila, Marina and Zhang, Tong}, volume = {139}, series = {Proceedings of Machine Learning Research}, month = {18--24 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v139/kiyasseh21a/kiyasseh21a.pdf}, url = {https://proceedings.mlr.press/v139/kiyasseh21a.html}, abstract = {The healthcare industry generates troves of unlabelled physiological data. This data can be exploited via contrastive learning, a self-supervised pre-training method that encourages representations of instances to be similar to one another. We propose a family of contrastive learning methods, CLOCS, that encourages representations across space, time, \textit{and} patients to be similar to one another. We show that CLOCS consistently outperforms the state-of-the-art methods, BYOL and SimCLR, when performing a linear evaluation of, and fine-tuning on, downstream tasks. We also show that CLOCS achieves strong generalization performance with only 25% of labelled training data. Furthermore, our training procedure naturally generates patient-specific representations that can be used to quantify patient-similarity.} }
Endnote
%0 Conference Paper %T CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patients %A Dani Kiyasseh %A Tingting Zhu %A David A Clifton %B Proceedings of the 38th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2021 %E Marina Meila %E Tong Zhang %F pmlr-v139-kiyasseh21a %I PMLR %P 5606--5615 %U https://proceedings.mlr.press/v139/kiyasseh21a.html %V 139 %X The healthcare industry generates troves of unlabelled physiological data. This data can be exploited via contrastive learning, a self-supervised pre-training method that encourages representations of instances to be similar to one another. We propose a family of contrastive learning methods, CLOCS, that encourages representations across space, time, \textit{and} patients to be similar to one another. We show that CLOCS consistently outperforms the state-of-the-art methods, BYOL and SimCLR, when performing a linear evaluation of, and fine-tuning on, downstream tasks. We also show that CLOCS achieves strong generalization performance with only 25% of labelled training data. Furthermore, our training procedure naturally generates patient-specific representations that can be used to quantify patient-similarity.
APA
Kiyasseh, D., Zhu, T. & Clifton, D.A.. (2021). CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patients. Proceedings of the 38th International Conference on Machine Learning, in Proceedings of Machine Learning Research 139:5606-5615 Available from https://proceedings.mlr.press/v139/kiyasseh21a.html.

Related Material