The DOI matches its Crossref record.
Deep Learning for Multivariate Time Series Imputation: A Survey
Abstract
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 is available at https://github.com/WenjieDu/Awesome_Imputation.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Depending on the cause, missing sensor values must be addressed in different ways, such as manual recalibration or data imputation.
“Depending on the cause, the failure must be addressed in different ways, such as manual recalibration or data imputation [71,72].”
From Case-Based Data Quality Management for IoT Logs: A Case Study Focusing on Detection of Data Quality Issues (2025) · cites this paper as [72]
Citations
Cited by
Sorted by citations
Time Series Information Visualization - A Review of Approaches and Tools
Ortigossa, E. S., Dias, F. F., do Nascimento, D. C., & Nonato, L. G. (2025) · IEEE Access · doi:10.1109/access.2025.3609404 · Cited by 6
Hao, Q., Liang, R., Gao, Y., et al. (2025) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2025.3594032 · Cited by 4
Chen, X., Wang, K., & Ye, Q. (2025) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2025.3569455 · Cited by 3
Xu, X., Hu, L., Miao, X., et al. (2026) · Journal of Hydrology · doi:10.1016/j.jhydrol.2026.134937 · Cited by 2
Deep sub-ensembles meets quantile regression: uncertainty-aware imputation for time series
Liu, Y., Cui, P., Hu, W., et al. (2025) · Machine Learning · doi:10.1007/s10994-025-06922-x · Cited by 2
Schultheis, A., Bertrand, Y., Grüger, J., Malburg, L., Bergmann, R., & Serral Asensio, E. (2025) · IoT · doi:10.3390/iot6040063 · Cited by 2
FTIM: An end-to-end flight trajectory imputation method
Wang, L., Wang, X., Zhang, J., et al. (2025) · Aerospace Science and Technology · doi:10.1016/j.ast.2025.111031 · Cited by 1
Liu, Z., Yang, F., Li, X., et al. (2026) · Agriculture · doi:10.3390/agriculture16030354 · Cited by 1
Optimizing-Time Series Imputation with Data Quality
Huang, F., Li, S. Y., Peng, J., et al. (2026) · Applied Sciences · doi:10.3390/app16146837 · Cited by 1
A Temporally Disentangled Contrastive Diffusion Model for Spatiotemporal Imputation
Chen, Y., Shi, K., Wu, Z., Chen, J., WANG, X., McAuley, J., Xu, G., & Yu, S. L. (2026) · CAAI Transactions on Intelligence Technology · doi:10.1049/cit2.70085 · Cited by 4
Diffusion-Based Imputation Method for Structured Missingness in Operational ESS Sites
Park, J.-W., Kim, C., & Choi, H.-S. (2025) · doi:10.1109/icufn65838.2025.11170107
MGDTSI: A Multiple Guidance Distillation-Based Model For Time Series Imputation
Li, K., Yuan, J., Zhang, J., et al. (2025) · doi:10.1109/ijcnn64981.2025.11229337
Song, H., Li, S., & Han, Q. (2025) · doi:10.1109/ijcnn64981.2025.11227658
Synergistic flood forecasting: combining physics-based and spatio-temporal deep learning models
Masoudimoghaddam, M., Espahbodinia, S., Yazdi, J., et al. (2025) · Hydrological Sciences Journal · doi:10.1080/02626667.2025.2604257
Clinically informed imputation of medical data using parallel diffusion models
Wang, S., Zhang, X., Jewell, S., et al. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130646
Huang, L., bin Jaharadak, A. A., Ahmad, N. I., et al. (2025) · IEEE Signal Processing Letters · doi:10.1109/lsp.2025.3639375
Self-citationMuniz, R., Lima, V., Saldanha, P., Ribeiro, A., de Paula, R., Cadeiras, M., da Silva, C., Silva, H., Rocha, P., & Pinheiro, D. (2025) · doi:10.5753/eniac.2025.13855
Transformer-Based Missing Data Imputation in Time Series With Application to Flight Test Data
Li, J., Li, L.-S., Dong, Y.-N., et al. (2026) · IEEE transactions on industrial electronics (1982. Print) · doi:10.1109/tie.2026.3672736 · Cited by 1
Başar, T., Djehiche, B., & Tembiné, H. (2025) · Static & dynamic game theory: foundations & applications · doi:10.1007/978-3-032-07031-9_8
DART: Diffusion-based approach for predicting trajectories of ballistic missiles
Kang, J., Lee, S., Yeom, J., Hong, D., Kim, Y., & Song, K. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.132065
Gong, N., Liang, S., Liu, L., Ni, Y., & Lei, Y. (2026) · Earthquake Engineering & Structural Dynamics · doi:10.1002/eqe.70191
Xue, S., & Zhang, L. (2026) · Journal of Systems Science and Complexity · doi:10.1007/s11424-026-5546-4
Jiang, D., Liu, C., & Xu, D. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.132712
Tian, H., Lu, S., Wang, H., et al. (2026) · Measurement Science and Technology · doi:10.1088/1361-6501/ae6abd
Ning, C., Zheng, T., Chen, Y., Huang, Y., Xu, X., Xu, H., Li, M., Zhao, R., Chen, R., Xia, J., et al. (2026) · Medical Image Analysis · doi:10.1016/j.media.2026.104132
Reconstruction of missing radiosonde observations for Indian region using conditional GAN framework
Singh, G., Durbha, S. S., Budakoti, S., et al. (2026) · Journal of Atmospheric and Solar-Terrestrial Physics · doi:10.1016/j.jastp.2026.106840
Li, T., Xing, X., Wei, D., Li, X., Guo, P., Xi, J., & Zhang, J. (2026) · steel research international · doi:10.1002/srin.70561
Adaptive Imputation for Daily Meteorological Time Series Under Bimodal Seasonal Regimes
Becerra-Suarez, F. L., Rodriguez-Avila, S., Arones-Perez, P. P., et al. (2026) · IEEE Access · doi:10.1109/access.2026.3711559
Academic Performance Forecasting via Data Imputation and Bayesian Neural Networks
Yamada, Y., Watanabe, K., Maeda, K., Ogawa, T., & Haseyama, M. (2026) · Applied Sciences · doi:10.3390/app16147350
Bai, H., Gan, Y., Qiu, P., et al. (2026) · International Conference on Electronic Information Technology and Computer Engineering (EITCE) · doi:10.1109/eitce70137.2026.11634553
Park, H., Heo, S. J., Lee, S., & Kim, Y. M. (2026) · Water Resources and Industry · doi:10.1016/j.wri.2026.100394
Metadata
- Authors
- Wang, J., Du, W., Yang, Y., Qian, L., Cao, W., Zhang, K., Wang, W., Liang, Y., & Wen, Q.
- Affiliations
- Hong Kong University of Science and Technology (HK)
- PyPOTS Research
- University of Oxford (GB)
- King's College London (GB)
- Huawei Technologies (China) (CN)
- The Hong Kong University of Science and Technology (Guangzhou) (CN)
- Squirrel Ai Learning
- ORCID
- Venue
- Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence
- Published
- 2024-08
- Pages
- 10696-10704
- OpenAlex
- W4414360835
- Cited by
- 43
- References
- 0
- Citations by year
- 2026: 17 · 2025: 21 · 2024: 5
- FWCI
- 16.13
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Joint Conference on Artificial Intelligence (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Signal Processing › Time Series Analysis and Forecasting
- Social Sciences › Transportation › Traffic Prediction and Management Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Anomaly Detection Techniques and Applications
- Keywords
- multivariate time series imputation, missing data, deep learning, imputation uncertainty, neural network architecture
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
