# SeqLink: A Robust Neural-ODE Architecture for Modelling Partially Observed Time Series

arXiv: https://arxiv.org/abs/2212.03560 · HTML: https://mlsanity.com/paper/2212.03560/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 35 references that are in the map.
- First posted on arXiv 7 Dec 2022.

## Builds on (most cited first, 22 of 22)

- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [Neural Controlled Differential Equations for Irregular Time Series](https://mlsanity.com/paper/2005.08926/) (2020)
- [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)
- [Neural Jump Stochastic Differential Equations](https://mlsanity.com/paper/1905.10403/) (2019)
- [Neural Rough Differential Equations for Long Time Series](https://mlsanity.com/paper/2009.08295/) (2020)
- [Modeling Irregular Time Series with Continuous Recurrent Units](https://mlsanity.com/paper/2111.11344/) (2021)
- [On Robustness of Neural Ordinary Differential Equations](https://mlsanity.com/paper/1910.05513/) (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 Jump Ordinary Differential Equations: Consistent Continuous-Time Prediction and Filtering](https://mlsanity.com/paper/2006.04727/) (2020)
- [Learning continuous models for continuous physics](https://mlsanity.com/paper/2202.08494/) (2022)
- [EXIT: Extrapolation and Interpolation-based Neural Controlled Differential Equations for Time-series Classification and Forecasting](https://mlsanity.com/paper/2204.08771/) (2022)
- [On Numerical Integration in Neural Ordinary Differential Equations](https://mlsanity.com/paper/2206.07335/) (2022)
- [ResNet After All? Neural ODEs and Their Numerical Solution](https://mlsanity.com/paper/2007.15386/) (2020)
- [Latent Neural ODEs with Sparse Bayesian Multiple Shooting](https://mlsanity.com/paper/2210.03466/) (2022)
- [Neural Ordinary Differential Equation based Recurrent Neural Network Model](https://mlsanity.com/paper/2005.09807/) (2020)
- [Multi-resolution Networks For Flexible Irregular Time Series Modeling (Multi-FIT)](https://mlsanity.com/paper/1905.00125/) (2019)
- [Generative time series models using Neural ODE in Variational Autoencoders](https://mlsanity.com/paper/2201.04630/) (2022)
- [PIETS: Parallelised Irregularity Encoders for Forecasting with Heterogeneous Time-Series](https://mlsanity.com/paper/2110.00071/) (2021)
- [Solar Power Time Series Forecasting Utilising Wavelet Coefficients](https://mlsanity.com/paper/2210.00269/) (2022)

## Built on by (most cited first, 4 of 4)

- [Universal Time-Series Representation Learning: A Survey](https://mlsanity.com/paper/2401.03717/) (2024)
- [SDE-Attention: Latent Attention in SDE-RNNs for Irregularly Sampled Time Series with Missing Data](https://mlsanity.com/paper/2511.23238/) (2025)
- [Perturbation Effects on Robustness and Individual Fairness](https://mlsanity.com/paper/2404.01356/) (2024)
- [ODEStream: A Buffer-Free Online Learning Framework with ODE-based Adaptor for Streaming Time Series Forecasting](https://mlsanity.com/paper/2411.07413/) (2024)

## Abstract (arXiv)

Ordinary Differential Equations (ODE) based models have become popular as foundation models for solving many time series problems. Combining neural ODEs with traditional RNN models has provided the best representation for irregular time series. However, ODE-based models typically require the trajectory of hidden states to be defined based on either the initial observed value or the most recent observation, raising questions about their effectiveness when dealing with longer sequences and extended time intervals. In this article, we explore the behaviour of the ODE models in the context of time series data with varying degrees of sparsity. We introduce SeqLink, an innovative neural architecture designed to enhance the robustness of sequence representation. Unlike traditional approaches that solely rely on the hidden state generated from the last observed value, SeqLink leverages ODE latent representations derived from multiple data samples, enabling it to generate robust data representations regardless of sequence length or data sparsity level. The core concept behind our model is the definition of hidden states for the unobserved values based on the relationships between samples (links between sequences). Through extensive experiments on partially observed synthetic and real-world datasets, we demonstrate that SeqLink improves the modelling of intermittent time series, consistently outperforming state-of-the-art approaches.