# Sequence Prediction Under Missing Data : An RNN Approach Without Imputation

arXiv: https://arxiv.org/abs/2208.08933 · HTML: https://mlsanity.com/paper/2208.08933/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 39 references that are in the map.
- First posted on arXiv 18 Aug 2022.

## Builds on (most cited first, 15 of 15)

- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Speech Recognition with Deep Recurrent Neural Networks](https://mlsanity.com/paper/1303.5778/) (2013)
- [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)
- [Time Series Forecasting With Deep Learning: A Survey](https://mlsanity.com/paper/2004.13408/) (2020)
- [BRITS: Bidirectional Recurrent Imputation for Time Series](https://mlsanity.com/paper/1805.10572/) (2018)
- [A Multi-Horizon Quantile Recurrent Forecaster](https://mlsanity.com/paper/1711.11053/) (2017)
- [Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models](https://mlsanity.com/paper/1411.2539/) (2014)
- [Modeling Missing Data in Clinical Time Series with RNNs](https://mlsanity.com/paper/1606.04130/) (2016)
- [Light Gated Recurrent Units for Speech Recognition](https://mlsanity.com/paper/1803.10225/) (2018)
- [A scalable end-to-end Gaussian process adapter for irregularly sampled time series classification](https://mlsanity.com/paper/1606.04443/) (2016)
- [Survey on the attention based RNN model and its applications in computer vision](https://mlsanity.com/paper/1601.06823/) (2016)

## Built on by (most cited first, 3 of 3)

- [GinAR: An End-To-End Multivariate Time Series Forecasting Model Suitable for Variable Missing](https://mlsanity.com/paper/2405.11333/) (2024)
- [CoRe-Sleep: A Multimodal Fusion Framework for Time Series Robust to Imperfect Modalities](https://mlsanity.com/paper/2304.06485/) (2023)
- [IBN: An Interpretable Bidirectional-Modeling Network for Multivariate Time Series Forecasting with Variable Missing](https://mlsanity.com/paper/2509.07725/) (2025)

## Abstract (arXiv)

Missing data scenarios are very common in ML applications in general and time-series/sequence applications are no exceptions. This paper pertains to a novel Recurrent Neural Network (RNN) based solution for sequence prediction under missing data. Our method is distinct from all existing approaches. It tries to encode the missingness patterns in the data directly without trying to impute data either before or during model building. Our encoding is lossless and achieves compression. It can be employed for both sequence classification and forecasting. We focus on forecasting here in a general context of multi-step prediction in presence of possible exogenous inputs. In particular, we propose novel variants of Encoder-Decoder (Seq2Seq) RNNs for this. The encoder here adopts the above mentioned pattern encoding, while at the decoder which has a different structure, multiple variants are feasible. We demonstrate the utility of our proposed architecture via multiple experiments on both single and multiple sequence (real) data-sets. We consider both scenarios where (i)data is naturally missing and (ii)data is synthetically masked.