mlsanityData to 7 Oct 2026

Continuous-time Autoencoders for Regular and Irregular Time Series Imputation

arXiv 2312.16581 ↗First posted 27 Dec 2023cs.LG cs.IRcited by 6

Not on the map. Why?

Abstract (arXiv)

Time series imputation is one of the most fundamental tasks for time series. Real-world time series datasets are frequently incomplete (or irregular with missing observations), in which case imputation is strongly required. Many different time series imputation methods have been proposed. Recent self-attention-based methods show the state-of-the-art imputation performance. However, it has been overlooked for a long time to design an imputation method based on continuous-time recurrent neural networks (RNNs), i.e., neural controlled differential equations (NCDEs). To this end, we redesign time series (variational) autoencoders based on NCDEs. Our method, called continuous-time autoencoder (CTA), encodes an input time series sample into a continuous hidden path (rather than a hidden vector) and decodes it to reconstruct and impute the input. In our experiments with 4 datasets and 19 baselines, our method shows the best imputation performance in almost all cases.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 29 of its 59 references that are in the map. First posted on arXiv 27 Dec 2023.

Builds on

29 of 59 references.

References · 29

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  3. 2018Neural Ordinary Differential Equationscited by 3,733
  4. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  5. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,428
  6. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,125
  7. 2017Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learningcited by 935
  8. 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 820
  9. 2016Recurrent Neural Networks for Multivariate Time Series with Missing Valuescited by 548
  10. 2020Neural Controlled Differential Equations for Irregular Time Seriescited by 501
  11. 2015A Recurrent Latent Variable Model for Sequential Datacited by 362
  12. 2018GAIN: Missing Data Imputation using Generative Adversarial Netscited by 349
17 more
  1. 2021Graph Neural Network for Traffic Forecasting: A Surveycited by 260
  2. 2020Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecastingcited by 212
  3. 2021Spatial-Temporal Graph ODE Networks for Traffic Flow Forecastingcited by 209
  4. 2019GP-VAE: Deep Probabilistic Time Series Imputationcited by 171
  5. 2022SAITS: Self-Attention-based Imputation for Time Seriescited by 167
  6. 2018Handling Incomplete Heterogeneous Data using VAEscited by 148
  7. 2021Graph Neural Controlled Differential Equations for Traffic Forecastingcited by 133
  8. 2020Dynamical Variational Autoencoders: A Comprehensive Reviewcited by 127
  9. 2016Sequential Neural Models with Stochastic Layerscited by 115
  10. 2017Estimating Missing Data in Temporal Data Streams Using Multi-directional Recurrent Neural Networkscited by 86
  11. 2014Learning Stochastic Recurrent Networkscited by 60
  12. 2020Applications of deep learning in stock market prediction: recent progresscited by 51
  13. 2021NRTSI: Non-Recurrent Time Series Imputationcited by 25
  14. 2019CDSA: Cross-Dimensional Self-Attention for Multivariate, Geo-tagged Time Series Imputationcited by 24
  15. 2021Climate Modeling with Neural Diffusion Equationscited by 20
  16. 2021Accurate Stock Price Forecasting Using Robust and Optimized Deep Learning Modelscited by 15
  17. 2023Graph Neural Rough Differential Equations for Traffic Forecastingcited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 2; 2026: 1.

6 papers.

  1. 2025Glocal Information Bottleneck for Time Series Imputationcited by 9
  2. 2024Balanced Neural ODEs: nonlinear model order reduction and Koopman operator approximationscited by 3
  3. 2024Sampling-guided Heterogeneous Graph Neural Network with Temporal Smoothing for Scalable Longitudinal Data Imputationcited by 2
  4. 2025Boundary-enhanced time series data imputation with long-term dependency diffusion modelscited by 2
  5. 2026InstructTime++: Time Series Classification with Multimodal Language Modeling via Implicit Feature Enhancementcited by 2
  6. 2024Bridging Dynamic Factor Models and Neural Controlled Differential Equations for Nowcasting GDPcited by 1