Set Functions for Time Series

Max Horn, Michael Moor, Christian Bock, Bastian Rieck, Karsten Borgwardt
Proceedings of the 37th International Conference on Machine Learning, PMLR 119:4353-4363, 2020.

Abstract

Despite the eminent successes of deep neural networks, many architectures are often hard to transfer to irregularly-sampled and asynchronous time series that commonly occur in real-world datasets, especially in healthcare applications. This paper proposes a novel approach for classifying irregularly-sampled time series with unaligned measurements, focusing on high scalability and data efficiency. Our method SeFT (Set Functions for Time Series) is based on recent advances in differentiable set function learning, extremely parallelizable with a beneficial memory footprint, thus scaling well to large datasets of long time series and online monitoring scenarios. Furthermore, our approach permits quantifying per-observation contributions to the classification outcome. We extensively compare our method with existing algorithms on multiple healthcare time series datasets and demonstrate that it performs competitively whilst significantly reducing runtime.

Cite this Paper


BibTeX
@InProceedings{pmlr-v119-horn20a, title = {Set Functions for Time Series}, author = {Horn, Max and Moor, Michael and Bock, Christian and Rieck, Bastian and Borgwardt, Karsten}, booktitle = {Proceedings of the 37th International Conference on Machine Learning}, pages = {4353--4363}, 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/horn20a/horn20a.pdf}, url = {http://proceedings.mlr.press/v119/horn20a.html}, abstract = {Despite the eminent successes of deep neural networks, many architectures are often hard to transfer to irregularly-sampled and asynchronous time series that commonly occur in real-world datasets, especially in healthcare applications. This paper proposes a novel approach for classifying irregularly-sampled time series with unaligned measurements, focusing on high scalability and data efficiency. Our method SeFT (Set Functions for Time Series) is based on recent advances in differentiable set function learning, extremely parallelizable with a beneficial memory footprint, thus scaling well to large datasets of long time series and online monitoring scenarios. Furthermore, our approach permits quantifying per-observation contributions to the classification outcome. We extensively compare our method with existing algorithms on multiple healthcare time series datasets and demonstrate that it performs competitively whilst significantly reducing runtime.} }
Endnote
%0 Conference Paper %T Set Functions for Time Series %A Max Horn %A Michael Moor %A Christian Bock %A Bastian Rieck %A Karsten Borgwardt %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-horn20a %I PMLR %P 4353--4363 %U http://proceedings.mlr.press/v119/horn20a.html %V 119 %X Despite the eminent successes of deep neural networks, many architectures are often hard to transfer to irregularly-sampled and asynchronous time series that commonly occur in real-world datasets, especially in healthcare applications. This paper proposes a novel approach for classifying irregularly-sampled time series with unaligned measurements, focusing on high scalability and data efficiency. Our method SeFT (Set Functions for Time Series) is based on recent advances in differentiable set function learning, extremely parallelizable with a beneficial memory footprint, thus scaling well to large datasets of long time series and online monitoring scenarios. Furthermore, our approach permits quantifying per-observation contributions to the classification outcome. We extensively compare our method with existing algorithms on multiple healthcare time series datasets and demonstrate that it performs competitively whilst significantly reducing runtime.
APA
Horn, M., Moor, M., Bock, C., Rieck, B. & Borgwardt, K.. (2020). Set Functions for Time Series. Proceedings of the 37th International Conference on Machine Learning, in Proceedings of Machine Learning Research 119:4353-4363 Available from http://proceedings.mlr.press/v119/horn20a.html.

Related Material