mlsanityData to 7 Oct 2026

Deep Learning for Multivariate Time Series Imputation: A Survey

arXiv 2402.04059 ↗First posted 6 Feb 2024cs.LG cs.AIcited by 57

Not on the map. Why?

Abstract (arXiv)

Missing values are ubiquitous in multivariate time series (MTS) data, posing significant challenges for accurate analysis and downstream applications. In recent years, deep learning-based methods have successfully handled missing data by leveraging complex temporal dependencies and learned data distributions. In this survey, we provide a comprehensive summary of deep learning approaches for multivariate time series imputation (MTSI) tasks. We propose a novel taxonomy that categorizes existing methods based on two key perspectives: imputation uncertainty and neural network architecture. Furthermore, we summarize existing MTSI toolkits with a particular emphasis on the PyPOTS Ecosystem, which provides an integrated and standardized foundation for MTSI research. Finally, we discuss key challenges and future research directions, which give insight for further MTSI research. This survey aims to serve as a valuable resource for researchers and practitioners in the field of time series analysis and missing data imputation tasks.A well-maintained MTSI paper and tool list are available at https://github.com/WenjieDu/Awesome_Imputation.

Key facts. Cited by 57 papers in the map (data through 7 Oct 2026). Builds on 35 of its 74 references that are in the map. First posted on arXiv 6 Feb 2024.

Builds on

35 of 74 references.

References · 35

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,424
  3. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  4. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
  5. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,030
  6. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 680
  7. 2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 615
  8. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 577
  9. 2016Recurrent Neural Networks for Multivariate Time Series with Missing Valuescited by 548
  10. 2022Transformers in Time Series: A Surveycited by 489
  11. 2017Real-valued (Medical) Time Series Generation with Recurrent Conditional GANscited by 329
  12. 2018BRITS: Bidirectional Recurrent Imputation for Time Seriescited by 288
23 more
  1. 2024Timer: Generative Pre-trained Transformers Are Large Time Series Modelscited by 198
  2. 2022Diffusion-based Time Series Imputation and Forecasting with Structured State Space Modelscited by 195
  3. 2019GP-VAE: Deep Probabilistic Time Series Imputationcited by 171
  4. 2022SAITS: Self-Attention-based Imputation for Time Seriescited by 167
  5. 2023Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlookcited by 109
  6. 2019sktime: A Unified Interface for Machine Learning with Time Seriescited by 98
  7. 2021Filling the G_ap_s: Multivariate Time Series Imputation by Graph Neural Networkscited by 93
  8. 2017Estimating Missing Data in Temporal Data Streams Using Multi-directional Recurrent Neural Networkscited by 86
  9. 2022Learning to Reconstruct Missing Data from Spatiotemporal Graphs with Sparse Observationscited by 64
  10. 2023PriSTI: A Conditional Diffusion Framework for Spatiotemporal Imputationcited by 62
  11. 2021MIRACLE: Causally-Aware Imputation via Learning Missing Data Mechanismscited by 50
  12. 2023ImputeFormer: Low Rankness-Induced Transformers for Generalizable Spatiotemporal Imputationcited by 50
  13. 2022Modeling Temporal Data as Continuous Functions with Stochastic Process Diffusioncited by 39
  14. 2020Time Series Data Imputation: A Survey on Deep Learning Approachescited by 34
  15. 2020Uncertainty-Aware Variational-Recurrent Imputation Network for Clinical Time Seriescited by 33
  16. 2021Missing Value Imputation on Multidimensional Time Seriescited by 33
  17. 2023Provably Convergent Schr"odinger Bridge with Applications to Probabilistic Time Series Imputationcited by 26
  18. 2021NRTSI: Non-Recurrent Time Series Imputationcited by 25
  19. 2019CDSA: Cross-Dimensional Self-Attention for Multivariate, Geo-tagged Time Series Imputationcited by 24
  20. 2023Probabilistic Imputation for Time-series Classification with Missing Datacited by 21
  21. 2023Data Imputation for Sparse Radio Maps in Indoor Positioning (Extended Version)cited by 6
  22. 2022Differentiable and Scalable Generative Adversarial Models for Data Imputationcited by 5
  23. 2023Enhancing Missing Data Imputation of Non-stationary Signals with Harmonic Decompositioncited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 18; 2025: 19; 2026: 20.

57 papers.

Sort:

By area:

  1. 2024Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Expertscited by 280
  2. 2024Foundation Models for Time Series Analysis: A Tutorial and Surveycited by 234
  3. 2024A Survey on Diffusion Models for Time Series and Spatio-Temporal Datacited by 66
  4. 2024TSI-Bench: Benchmarking Time Series Imputationcited by 33
  5. 2025Foundation Models for Time Series: A Surveycited by 19
  6. 2025Time-IMM: A Dataset and Benchmark for Irregular Multimodal Multivariate Time Seriescited by 16
  7. 2024Zero-shot Imputation with Foundation Inference Models for Dynamical Systemscited by 13
  8. 2024Causality-Aware Spatiotemporal Graph Neural Networks for Spatiotemporal Time Series Imputationcited by 11
  9. 2025BEDTime: A Unified Benchmark for Automatically Describing Time Seriescited by 11
  10. 2024TimeCHEAT: A Channel Harmony Strategy for Irregularly Sampled Multivariate Time Series Analysiscited by 10
  11. 2025Glocal Information Bottleneck for Time Series Imputationcited by 9
  12. 2026TSAQA: Time Series Analysis Question And Answering Benchmarkcited by 8
38 more
  1. 2024Beyond Random Missingness: Clinically Rethinking for Healthcare Time Series Imputationcited by 6
  2. 2024Task-oriented Time Series Imputation Evaluation via Generalized Representerscited by 6
  3. 2024How Deep is your Guess? A Fresh Perspective on Deep Learning for Medical Time-Series Imputationcited by 5
  4. 2024A Temporally Disentangled Contrastive Diffusion Model for Spatiotemporal Imputationcited by 4
  5. 2024NuwaTS: a Foundation Model Mending Every Incomplete Time Seriescited by 4
  6. 2024Rethinking the Diffusion Models for Numerical Tabular Data Imputation from the Perspective of Wasserstein Gradient Flowcited by 3
  7. 2024Using matrix-product states for time-series machine learningcited by 2
  8. 2025Bridging Smart Meter Gaps: A Benchmark of Statistical, Machine Learning and Time Series Foundation Models for Data Imputationcited by 2
  9. 2025IMTS is Worth Time × Channel Patches: Visual Masked Autoencoders for Irregular Multivariate Time Series Predictioncited by 2
  10. 2025MoGU: Mixture-of-Gaussians with Uncertainty-based Gating for Time Series Forecastingcited by 2
  11. 2025FADTI: Fourier and Attention Driven Diffusion for Multivariate Time Series Imputationcited by 2
  12. 2026Learning to Factorize and Adapt: A Versatile Approach Toward Universal Spatio-Temporal Foundation Modelscited by 2
  13. 2026Multi-scale hypergraph meets LLMs: Aligning large language models for time series analysiscited by 2
  14. 2026T1: One-to-One Channel-Head Binding for Multivariate Time-Series Imputationcited by 2
  15. 2024TIMBA: Time series Imputation with Bi-directional Mamba Blocks and Diffusion modelscited by 1
  16. 2025Integrating Sequence and Image Modeling in Irregular Medical Time Series Through Self-Supervised Learningcited by 1
  17. 2025CoIFNet: A Unified Framework for Multivariate Time Series Forecasting with Missing Valuescited by 1
  18. 2026Spatial-Temporal Feedback Diffusion Guidance for Controlled Traffic Imputationcited by 1
  19. 2026HELIX: Hybrid Encoding with Learnable Identity and Cross-dimensional Synthesis for Time Series Imputationcited by 1
  20. 2026AION: Next-Generation Tasks and Practical Harness for Time Seriescited by 1
  21. 2026TRACE: A Temporal Conditional Estimation for Multimodal Time Series Foundation Modelscited by 1
  22. 2026Anomaly Detection for Sparse and Irregular Multivariate Time Series with Latent SDEscited by 1
  23. 2024Is Precise Recovery Necessary? A Task-Oriented Imputation Approach for Time Series Forecasting on Variable Subsetcited by 0
  24. 2024MuSiCNet: A Gradual Coarse-to-Fine Framework for Irregularly Sampled Multivariate Time Series Analysiscited by 0
  25. 2024A Survey and Benchmarking of Spatial-Temporal Traffic Data Imputation Modelscited by 0
  26. 2025NeuralPrefix: A Zero-shot Sensory Data Imputation Plugincited by 0
  27. 2025A new membership inference attack that spots memorization in generative and predictive models: Loss-Based with Reference Model algorithm (LBRM)cited by 0
  28. 2025Imputation of Missing Data in Smooth Pursuit Eye Movements Using a Self-Attention-based Deep Learning Approachcited by 0
  29. 2025From Time Series Analysis to Question Answering: A Survey in the LLM Eracited by 0
  30. 2025Hallucination Detection and Mitigation with Diffusion in Multi-Variate Time-Series Foundation Modelscited by 0
  31. 2025An Improved Time Series Anomaly Detection by Applying Structural Similaritycited by 0
  32. 2025Diffusion Transformers for Imputation: Statistical Efficiency and Uncertainty Quantificationcited by 0
  33. 2025An Interdisciplinary and Cross-Task Review on Missing Data Imputationcited by 0
  34. 2025IBMA: An Imputation-Based Mixup Augmentation Using Self-Supervised Learning for Time Series Datacited by 0
  35. 2026A Unified Variational Imputation Framework for Electric Vehicle Charging Data Using Retrieval-Augmented Language Modelcited by 0
  36. 2026Beyond Static Uncertainty: Modeling Temporal Uncertainty Dynamics for Probabilistic Time Series Forecastingcited by 0
  37. 2026Conditional Imputation for Within-Modality Missingness in Multi-Modal Federated Learningcited by 0
  38. 2026End-to-End Learning for Partially-Observed Time Series with PyPOTScited by 0

50 most cited of 57 All 57 (JSON)