mlsanityData to 7 Oct 2026

NRTSI: Non-Recurrent Time Series Imputation

arXiv 2102.03340 ↗First posted 5 Feb 2021cs.LGcited by 25

Not on the map. Why?

Abstract (arXiv)

Time series imputation is a fundamental task for understanding time series with missing data. Existing methods either do not directly handle irregularly-sampled data or degrade severely with sparsely observed data. In this work, we reformulate time series as permutation-equivariant sets and propose a novel imputation model NRTSI that does not impose any recurrent structures. Taking advantage of the permutation equivariant formulation, we design a principled and efficient hierarchical imputation procedure. In addition, NRTSI can directly handle irregularly-sampled time series, perform multiple-mode stochastic imputation, and handle data with partially observed dimensions. Empirically, we show that NRTSI achieves state-of-the-art performance across a wide range of time series imputation benchmarks.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 37 of its 61 references that are in the map. First posted on arXiv 5 Feb 2021.

Builds on

37 of 61 references.

References · 37

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2016Layer Normalizationcited by 5,579
  5. 2018Neural Ordinary Differential Equationscited by 3,733
  6. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  7. 2017Deep Setscited by 1,394
  8. 2018Self-Attention with Relative Position Representationscited by 1,112
  9. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,024
  10. 2018DeepMind Control Suitecited by 935
  11. 2016Recurrent Neural Networks for Multivariate Time Series with Missing Valuescited by 548
  12. 2016Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networkscited by 541
25 more
  1. 2020Neural Controlled Differential Equations for Irregular Time Seriescited by 501
  2. 2018Conditional Neural Processescited by 421
  3. 2018GAIN: Missing Data Imputation using Generative Adversarial Netscited by 349
  4. 2018Generating Wikipedia by Summarizing Long Sequencescited by 333
  5. 2018Neural Processescited by 307
  6. 2018BRITS: Bidirectional Recurrent Imputation for Time Seriescited by 288
  7. 2019Attentive Neural Processescited by 280
  8. 2018Scalable and accurate deep learning for electronic health recordscited by 275
  9. 2021Multi-Time Attention Networks for Irregularly Sampled Time Seriescited by 234
  10. 2019GRU-ODE-Bayes: Continuous modeling of sporadically-observed time seriescited by 230
  11. 2019Latent ODEs for Irregularly-Sampled Time Seriescited by 182
  12. 2019Set Functions for Time Seriescited by 137
  13. 2018Lipschitz Continuity in Model-based Reinforcement Learningcited by 90
  14. 2018MaskGAN: Better Text Generation via Filling in the______cited by 89
  15. 2020Learning Long-Term Dependencies in Irregularly-Sampled Time Seriescited by 82
  16. 2016Modeling Missing Data in Clinical Time Series with RNNscited by 80
  17. 2020Diverse and Admissible Trajectory Forecasting through Multimodal Context Understandingcited by 68
  18. 2019NAOMI: Non-Autoregressive Multiresolution Sequence Imputationcited by 59
  19. 2019Self-attention with Functional Time Representation Learningcited by 52
  20. 2019Flow Models for Arbitrary Conditional Likelihoodscited by 30
  21. 2019CDSA: Cross-Dimensional Self-Attention for Multivariate, Geo-tagged Time Series Imputationcited by 24
  22. 2020Exchangeable Neural ODE for Set Modelingcited by 19
  23. 2019Meta-Neighborhoodscited by 9
  24. 2020RDIS: Random Drop Imputation with Self-Training for Incomplete Time Series Datacited by 7
  25. 2016End-to-End Subtitle Detection and Recognition for Videos in East Asian Languages via CNN Ensemble with Near-Human-Level Performancecited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 6; 2024: 9; 2025: 3; 2026: 2.

25 papers.

Sort:

By area:

  1. 2022Diffusion-based Time Series Imputation and Forecasting with Structured State Space Modelscited by 195
  2. 2022SAITS: Self-Attention-based Imputation for Time Seriescited by 167
  3. 2022Learning to Reconstruct Missing Data from Spatiotemporal Graphs with Sparse Observationscited by 64
  4. 2024Deep Learning for Multivariate Time Series Imputation: A Surveycited by 57
  5. 2023ImputeFormer: Low Rankness-Induced Transformers for Generalizable Spatiotemporal Imputationcited by 50
  6. 2024GinAR: An End-To-End Multivariate Time Series Forecasting Model Suitable for Variable Missingcited by 20
  7. 2024Causality-Aware Spatiotemporal Graph Neural Networks for Spatiotemporal Time Series Imputationcited by 11
  8. 2023Phoneme Hallucinator: One-shot Voice Conversion via Set Expansioncited by 9
  9. 2024Pedestrian Trajectory Prediction with Missing Data: Datasets, Imputation, and Benchmarkingcited by 8
  10. 2023Correlated Attention in Transformers for Multivariate Time Seriescited by 6
  11. 2023Continuous-time Autoencoders for Regular and Irregular Time Series Imputationcited by 6
  12. 2023Understand Legal Documents with Contextualized Large Language Modelscited by 5
13 more
  1. 2024How Deep is your Guess? A Fresh Perspective on Deep Learning for Medical Time-Series Imputationcited by 5
  2. 2024Learnable Prompt as Pseudo-Imputation: Rethinking the Necessity of Traditional EHR Data Imputation in Downstream Clinical Predictioncited by 4
  3. 2022Transparent Single-Cell Set Classification with Kernel Mean Embeddingscited by 3
  4. 2024Trajectory Imputation in Multi-Agent Sports with Derivative-Accumulating Self-Ensemblecited by 3
  5. 2025ImputeINR: Time Series Imputation via Implicit Neural Representations for Disease Diagnosis with Missing Datacited by 3
  6. 2023An End-to-End Time Series Model for Simultaneous Imputation and Forecastcited by 2
  7. 2025MTM: A Multi-Scale Token Mixing Transformer for Irregular Multivariate Time Series Classificationcited by 2
  8. 2024Towards Cost Sensitive Decision Makingcited by 1
  9. 2022Multistage Large Segment Imputation Framework Based on Deep Learning and Statistic Metricscited by 0
  10. 2024PIAD-SRNN: Physics-Informed Adaptive Decomposition in State-Space RNNcited by 0
  11. 2025STDiff: A State Transition Diffusion Framework for Time Series Imputation in Industrial Systemscited by 0
  12. 2026A Decomposable Forward Process in Diffusion Models for Time-Series Forecastingcited by 0
  13. 2026RDDMPI: Residual Denoising Diffusion Model for Probabilistic Multivariate Time Series Imputationcited by 0