# Finding Short Signals in Long Irregular Time Series with Continuous-Time Attention Policy Networks

arXiv: https://arxiv.org/abs/2302.04052 · HTML: https://mlsanity.com/paper/2302.04052/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 38 references that are in the map.
- First posted on arXiv 8 Feb 2023.

## Builds on (most cited first, 27 of 27)

- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Recurrent Neural Networks for Multivariate Time Series with Missing Values](https://mlsanity.com/paper/1606.01865/) (2016)
- [Neural Controlled Differential Equations for Irregular Time Series](https://mlsanity.com/paper/2005.08926/) (2020)
- [Recurrent Models of Visual Attention](https://mlsanity.com/paper/1406.6247/) (2014)
- [BRITS: Bidirectional Recurrent Imputation for Time Series](https://mlsanity.com/paper/1805.10572/) (2018)
- [Multi-Time Attention Networks for Irregularly Sampled Time Series](https://mlsanity.com/paper/2101.10318/) (2021)
- [GRU-ODE-Bayes: Continuous modeling of sporadically-observed time series](https://mlsanity.com/paper/1905.12374/) (2019)
- [Liquid Time-constant Networks](https://mlsanity.com/paper/2006.04439/) (2020)
- [Neural Jump Stochastic Differential Equations](https://mlsanity.com/paper/1905.10403/) (2019)
- [Modeling Irregular Time Series with Continuous Recurrent Units](https://mlsanity.com/paper/2111.11344/) (2021)
- [Interpolation-Prediction Networks for Irregularly Sampled Time Series](https://mlsanity.com/paper/1909.07782/) (2019)
- [Learning Long-Term Dependencies in Irregularly-Sampled Time Series](https://mlsanity.com/paper/2006.04418/) (2020)
- [Modeling Missing Data in Clinical Time Series with RNNs](https://mlsanity.com/paper/1606.04130/) (2016)
- [Neural Stochastic PDEs: Resolution-Invariant Learning of Continuous Spatiotemporal Dynamics](https://mlsanity.com/paper/2110.10249/) (2021)
- [HOLMES: Health OnLine Model Ensemble Serving for Deep Learning Models in Intensive Care Units](https://mlsanity.com/paper/2008.04063/) (2020)
- [Improving Natural Language Processing Tasks with Human Gaze-Guided Neural Attention](https://mlsanity.com/paper/2010.07891/) (2020)
- [Recognizing Detailed Human Context In-the-Wild from Smartphones and Smartwatches](https://mlsanity.com/paper/1609.06354/) (2016)
- [Attention Models in Graphs: A Survey](https://mlsanity.com/paper/1807.07984/) (2018)
- [Learning from Irregularly-Sampled Time Series: A Missing Data Perspective](https://mlsanity.com/paper/2008.07599/) (2020)
- [Discrete Event, Continuous Time RNNs](https://mlsanity.com/paper/1710.04110/) (2017)
- [A scalable end-to-end Gaussian process adapter for irregularly sampled time series classification](https://mlsanity.com/paper/1606.04443/) (2016)
- [Input-Cell Attention Reduces Vanishing Saliency of Recurrent Neural Networks](https://mlsanity.com/paper/1910.12370/) (2019)
- [Learning to Exploit Invariances in Clinical Time-Series Data using Sequence Transformer Networks](https://mlsanity.com/paper/1808.06725/) (2018)
- [Stop&Hop: Early Classification of Irregular Time Series](https://mlsanity.com/paper/2208.09795/) (2022)
- [Multi-resolution Networks For Flexible Irregular Time Series Modeling (Multi-FIT)](https://mlsanity.com/paper/1905.00125/) (2019)
- [Generalised Interpretable Shapelets for Irregular Time Series](https://mlsanity.com/paper/2005.13948/) (2020)

## Built on by (most cited first, 2 of 2)

- [Anomaly Detection and Generation with Diffusion Models: A Survey](https://mlsanity.com/paper/2506.09368/) (2025)
- [Continuous Time Evidential Distributions for Irregular Time Series](https://mlsanity.com/paper/2307.13503/) (2023)

## Abstract (arXiv)

Irregularly-sampled time series (ITS) are native to high-impact domains like healthcare, where measurements are collected over time at uneven intervals. However, for many classification problems, only small portions of long time series are often relevant to the class label. In this case, existing ITS models often fail to classify long series since they rely on careful imputation, which easily over- or under-samples the relevant regions. Using this insight, we then propose CAT, a model that classifies multivariate ITS by explicitly seeking highly-relevant portions of an input series' timeline. CAT achieves this by integrating three components: (1) A Moment Network learns to seek relevant moments in an ITS's continuous timeline using reinforcement learning. (2) A Receptor Network models the temporal dynamics of both observations and their timing localized around predicted moments. (3) A recurrent Transition Model models the sequence of transitions between these moments, cultivating a representation with which the series is classified. Using synthetic and real data, we find that CAT outperforms ten state-of-the-art methods by finding short signals in long irregular time series.