# Discrete Event, Continuous Time RNNs

arXiv: https://arxiv.org/abs/1710.04110 · HTML: https://mlsanity.com/paper/1710.04110/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Oct 2017.

## Built on by (most cited first, 30 of 31)

- [Multi-Time Attention Networks for Irregularly Sampled Time Series](https://mlsanity.com/paper/2101.10318/) (2021)
- [Modeling Irregular Time Series with Continuous Recurrent Units](https://mlsanity.com/paper/2111.11344/) (2021)
- [Closed-form Continuous-time Neural Models](https://mlsanity.com/paper/2106.13898/) (2021)
- [ContiFormer: Continuous-Time Transformer for Irregular Time Series Modeling](https://mlsanity.com/paper/2402.10635/) (2024)
- [Warpformer: A Multi-scale Modeling Approach for Irregular Clinical Time Series](https://mlsanity.com/paper/2306.09368/) (2023)
- [Neural Point Process for Learning Spatiotemporal Event Dynamics](https://mlsanity.com/paper/2112.06351/) (2021)
- [Stable Neural Stochastic Differential Equations in Analyzing Irregular Time Series Data](https://mlsanity.com/paper/2402.14989/) (2024)
- [Variable-rate discrete representation learning](https://mlsanity.com/paper/2103.06089/) (2021)
- [Causal Navigation by Continuous-time Neural Networks](https://mlsanity.com/paper/2106.08314/) (2021)
- [Comprehensive Review of Neural Differential Equations for Time Series Analysis](https://mlsanity.com/paper/2502.09885/) (2025)
- [DuETT: Dual Event Time Transformer for Electronic Health Records](https://mlsanity.com/paper/2304.13017/) (2023)
- [Stop&Hop: Early Classification of Irregular Time Series](https://mlsanity.com/paper/2208.09795/) (2022)
- [DeepJoint: Robust Survival Modelling Under Clinical Presence Shift](https://mlsanity.com/paper/2205.13481/) (2022)
- [Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series](https://mlsanity.com/paper/2308.03210/) (2023)
- [Irregularity-Informed Time Series Analysis: Adaptive Modelling of Spatial and Temporal Dynamics](https://mlsanity.com/paper/2410.12257/) (2024)
- [Learning to Decouple Complex Systems](https://mlsanity.com/paper/2302.01581/) (2023)
- [Neural Predictive Control to Coordinate Discrete- and Continuous-Time Models for Time-Series Analysis with Control-Theoretical Improvements](https://mlsanity.com/paper/2508.01833/) (2025)
- [HyMaTE: A Hybrid Mamba and Transformer Model for EHR Representation Learning](https://mlsanity.com/paper/2509.24118/) (2025)
- [Piecewise-constant Neural ODEs](https://mlsanity.com/paper/2106.06621/) (2021)
- [Finding Short Signals in Long Irregular Time Series with Continuous-Time Attention Policy Networks](https://mlsanity.com/paper/2302.04052/) (2023)
- [Anamnesic Neural Differential Equations with Orthogonal Polynomial Projections](https://mlsanity.com/paper/2303.01841/) (2023)
- [Prediction of Survival Outcomes under Clinical Presence Shift: A Joint Neural Network Architecture](https://mlsanity.com/paper/2508.05472/) (2025)
- [Task-Synchronized Recurrent Neural Networks](https://mlsanity.com/paper/2204.05192/) (2022)
- [SDE-Attention: Latent Attention in SDE-RNNs for Irregularly Sampled Time Series with Missing Data](https://mlsanity.com/paper/2511.23238/) (2025)
- [GRU-TV: Time- and velocity-aware GRU for patient representation on multivariate clinical time-series data](https://mlsanity.com/paper/2205.04892/) (2022)
- [Deep-Learning vs Regression: Prediction of Tourism Flow with Limited Data](https://mlsanity.com/paper/2206.13274/) (2022)
- [Continuous Depth Recurrent Neural Differential Equations](https://mlsanity.com/paper/2212.13714/) (2022)
- [Probabilistic Learning of Multivariate Time Series with Temporal Irregularity](https://mlsanity.com/paper/2306.09147/) (2023)
- [Continuous Time Evidential Distributions for Irregular Time Series](https://mlsanity.com/paper/2307.13503/) (2023)
- [Prediction of Tourism Flow with Sparse Geolocation Data](https://mlsanity.com/paper/2308.14516/) (2023)

## Abstract (arXiv)

We investigate recurrent neural network architectures for event-sequence processing. Event sequences, characterized by discrete observations stamped with continuous-valued times of occurrence, are challenging due to the potentially wide dynamic range of relevant time scales as well as interactions between time scales. We describe four forms of inductive bias that should benefit architectures for event sequences: temporal locality, position and scale homogeneity, and scale interdependence. We extend the popular gated recurrent unit (GRU) architecture to incorporate these biases via intrinsic temporal dynamics, obtaining a continuous-time GRU. The CT-GRU arises by interpreting the gates of a GRU as selecting a time scale of memory, and the CT-GRU generalizes the GRU by incorporating multiple time scales of memory and performing context-dependent selection of time scales for information storage and retrieval. Event time-stamps drive decay dynamics of the CT-GRU, whereas they serve as generic additional inputs to the GRU. Despite the very different manner in which the two models consider time, their performance on eleven data sets we examined is essentially identical. Our surprising results point both to the robustness of GRU and LSTM architectures for handling continuous time, and to the potency of incorporating continuous dynamics into neural architectures.