# Bidirectional Recurrent Neural Networks as Generative Models - Reconstructing Gaps in Time Series

arXiv: https://arxiv.org/abs/1504.01575 · HTML: https://mlsanity.com/paper/1504.01575/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Apr 2015.

## Built on by (most cited first, 14 of 14)

- [Machine Generated Text: A Comprehensive Survey of Threat Models and Detection Methods](https://mlsanity.com/paper/2210.07321/) (2022)
- [projUNN: efficient method for training deep networks with unitary matrices](https://mlsanity.com/paper/2203.05483/) (2022)
- [Parallel Refinements for Lexically Constrained Text Generation with BART](https://mlsanity.com/paper/2109.12487/) (2021)
- [From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation](https://mlsanity.com/paper/2409.19132/) (2024)
- [QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine Translation](https://mlsanity.com/paper/2406.00049/) (2024)
- [Show Me How To Revise: Improving Lexically Constrained Sentence Generation with XLNet](https://mlsanity.com/paper/2109.05797/) (2021)
- [Dynamic Spatiotemporal Graph Convolutional Neural Networks for Traffic Data Imputation with Complex Missing Patterns](https://mlsanity.com/paper/2109.08357/) (2021)
- [Deep Cellular Recurrent Network for Efficient Analysis of Time-Series Data with Spatial Information](https://mlsanity.com/paper/2101.05608/) (2021)
- [Imputation with Inter-Series Information from Prototypes for Irregular Sampled Time Series](https://mlsanity.com/paper/2401.07249/) (2024)
- [Diversity-Promoting Human Motion Interpolation via Conditional Variational Auto-Encoder](https://mlsanity.com/paper/2111.06762/) (2021)
- [Automated data-driven approach for gap filling in the time series using evolutionary learning](https://mlsanity.com/paper/2103.01124/) (2021)
- [Learning a Word-Level Language Model with Sentence-Level Noise Contrastive Estimation for Contextual Sentence Probability Estimation](https://mlsanity.com/paper/2103.07875/) (2021)
- [Monitoring Time Series With Missing Values: a Deep Probabilistic Approach](https://mlsanity.com/paper/2203.04916/) (2022)
- [A Latent Feature Analysis-based Approach for Spatio-Temporal Traffic Data Recovery](https://mlsanity.com/paper/2208.07739/) (2022)

## Abstract (arXiv)

Bidirectional recurrent neural networks (RNN) are trained to predict both in the positive and negative time directions simultaneously. They have not been used commonly in unsupervised tasks, because a probabilistic interpretation of the model has been difficult. Recently, two different frameworks, GSN and NADE, provide a connection between reconstruction and probabilistic modeling, which makes the interpretation possible. As far as we know, neither GSN or NADE have been studied in the context of time series before. As an example of an unsupervised task, we study the problem of filling in gaps in high-dimensional time series with complex dynamics. Although unidirectional RNNs have recently been trained successfully to model such time series, inference in the negative time direction is non-trivial. We propose two probabilistic interpretations of bidirectional RNNs that can be used to reconstruct missing gaps efficiently. Our experiments on text data show that both proposed methods are much more accurate than unidirectional reconstructions, although a bit less accurate than a computationally complex bidirectional Bayesian inference on the unidirectional RNN. We also provide results on music data for which the Bayesian inference is computationally infeasible, demonstrating the scalability of the proposed methods.