Modeling Irregular Time Series with Continuous Recurrent Units

Mona Schirmer, Mazin Eltayeb, Stefan Lessmann, Maja Rudolph
Proceedings of the 39th International Conference on Machine Learning, PMLR 162:19388-19405, 2022.

Abstract

Recurrent neural networks (RNNs) are a popular choice for modeling sequential data. Modern RNN architectures assume constant time-intervals between observations. However, in many datasets (e.g. medical records) observation times are irregular and can carry important information. To address this challenge, we propose continuous recurrent units (CRUs) {–} a neural architecture that can naturally handle irregular intervals between observations. The CRU assumes a hidden state, which evolves according to a linear stochastic differential equation and is integrated into an encoder-decoder framework. The recursive computations of the CRU can be derived using the continuous-discrete Kalman filter and are in closed form. The resulting recurrent architecture has temporal continuity between hidden states and a gating mechanism that can optimally integrate noisy observations. We derive an efficient parameterization scheme for the CRU that leads to a fast implementation f-CRU. We empirically study the CRU on a number of challenging datasets and find that it can interpolate irregular time series better than methods based on neural ordinary differential equations.

Cite this Paper


BibTeX
@InProceedings{pmlr-v162-schirmer22a, title = {Modeling Irregular Time Series with Continuous Recurrent Units}, author = {Schirmer, Mona and Eltayeb, Mazin and Lessmann, Stefan and Rudolph, Maja}, booktitle = {Proceedings of the 39th International Conference on Machine Learning}, pages = {19388--19405}, year = {2022}, editor = {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan}, volume = {162}, series = {Proceedings of Machine Learning Research}, month = {17--23 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v162/schirmer22a/schirmer22a.pdf}, url = {https://proceedings.mlr.press/v162/schirmer22a.html}, abstract = {Recurrent neural networks (RNNs) are a popular choice for modeling sequential data. Modern RNN architectures assume constant time-intervals between observations. However, in many datasets (e.g. medical records) observation times are irregular and can carry important information. To address this challenge, we propose continuous recurrent units (CRUs) {–} a neural architecture that can naturally handle irregular intervals between observations. The CRU assumes a hidden state, which evolves according to a linear stochastic differential equation and is integrated into an encoder-decoder framework. The recursive computations of the CRU can be derived using the continuous-discrete Kalman filter and are in closed form. The resulting recurrent architecture has temporal continuity between hidden states and a gating mechanism that can optimally integrate noisy observations. We derive an efficient parameterization scheme for the CRU that leads to a fast implementation f-CRU. We empirically study the CRU on a number of challenging datasets and find that it can interpolate irregular time series better than methods based on neural ordinary differential equations.} }
Endnote
%0 Conference Paper %T Modeling Irregular Time Series with Continuous Recurrent Units %A Mona Schirmer %A Mazin Eltayeb %A Stefan Lessmann %A Maja Rudolph %B Proceedings of the 39th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2022 %E Kamalika Chaudhuri %E Stefanie Jegelka %E Le Song %E Csaba Szepesvari %E Gang Niu %E Sivan Sabato %F pmlr-v162-schirmer22a %I PMLR %P 19388--19405 %U https://proceedings.mlr.press/v162/schirmer22a.html %V 162 %X Recurrent neural networks (RNNs) are a popular choice for modeling sequential data. Modern RNN architectures assume constant time-intervals between observations. However, in many datasets (e.g. medical records) observation times are irregular and can carry important information. To address this challenge, we propose continuous recurrent units (CRUs) {–} a neural architecture that can naturally handle irregular intervals between observations. The CRU assumes a hidden state, which evolves according to a linear stochastic differential equation and is integrated into an encoder-decoder framework. The recursive computations of the CRU can be derived using the continuous-discrete Kalman filter and are in closed form. The resulting recurrent architecture has temporal continuity between hidden states and a gating mechanism that can optimally integrate noisy observations. We derive an efficient parameterization scheme for the CRU that leads to a fast implementation f-CRU. We empirically study the CRU on a number of challenging datasets and find that it can interpolate irregular time series better than methods based on neural ordinary differential equations.
APA
Schirmer, M., Eltayeb, M., Lessmann, S. & Rudolph, M.. (2022). Modeling Irregular Time Series with Continuous Recurrent Units. Proceedings of the 39th International Conference on Machine Learning, in Proceedings of Machine Learning Research 162:19388-19405 Available from https://proceedings.mlr.press/v162/schirmer22a.html.

Related Material