mlsanityData to 7 Oct 2026

TSI-Bench: Benchmarking Time Series Imputation

arXiv 2406.12747 ↗First posted 18 Jun 2024cs.LG cs.AIcited by 33

Not on the map. Why?

Abstract (arXiv)

Effective imputation is a crucial preprocessing step for time series analysis. Despite the development of numerous deep learning algorithms for time series imputation, the community lacks standardized and comprehensive benchmark platforms to effectively evaluate imputation performance across different settings. Moreover, although many deep learning forecasting algorithms have demonstrated excellent performance, whether their modelling achievements can be transferred to time series imputation tasks remains unexplored. To bridge these gaps, we develop TSI-Bench, the first (to our knowledge) comprehensive benchmark suite for time series imputation utilizing deep learning techniques. The TSI-Bench pipeline standardizes experimental settings to enable fair evaluation of imputation algorithms and identification of meaningful insights into the influence of domain-appropriate missing rates and patterns on model performance. Furthermore, TSI-Bench innovatively provides a systematic paradigm to tailor time series forecasting algorithms for imputation purposes. Our extensive study across 34,804 experiments, 28 algorithms, and 8 datasets with diverse missingness scenarios demonstrates TSI-Bench's effectiveness in diverse downstream tasks and potential to unlock future directions in time series imputation research and analysis. All source code and experiment logs are released at https://github.com/WenjieDu/AwesomeImputation.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). Builds on 30 of its 72 references that are in the map. First posted on arXiv 18 Jun 2024.

Builds on

30 of 72 references.

References · 30

  1. 2017Attention Is All You Needcited by 59,932
  2. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 1,981
  3. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,654
  4. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  5. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,030
  6. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 906
  7. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 577
  8. 2022Non-stationary Transformers: Exploring the Stationarity in Time Series Forecastingcited by 385
  9. 2021SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interactioncited by 335
  10. 2021Spectral Temporal Graph Neural Network for Multivariate Time-series Forecastingcited by 298
  11. 2018BRITS: Bidirectional Recurrent Imputation for Time Seriescited by 288
  12. 2023TSMixer: An All-MLP Architecture for Time Series Forecastingcited by 232
18 more
  1. 2022Diffusion-based Time Series Imputation and Forecasting with Structured State Space Modelscited by 195
  2. 2019GP-VAE: Deep Probabilistic Time Series Imputationcited by 171
  3. 2023Frequency-domain MLPs are More Effective Learners in Time Series Forecastingcited by 170
  4. 2022FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecastingcited by 147
  5. 2022ETSformer: Exponential Smoothing Transformers for Time-series Forecastingcited by 146
  6. 2023A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detectioncited by 145
  7. 2023Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictorscited by 110
  8. 2021Filling the G_ap_s: Multivariate Time Series Imputation by Graph Neural Networkscited by 93
  9. 2024A Survey on Diffusion Models for Time Series and Spatio-Temporal Datacited by 66
  10. 2022Learning to Reconstruct Missing Data from Spatiotemporal Graphs with Sparse Observationscited by 64
  11. 2024Deep Learning for Multivariate Time Series Imputation: A Surveycited by 57
  12. 2020Time Series Data Imputation: A Survey on Deep Learning Approachescited by 34
  13. 2023Provably Convergent Schr"odinger Bridge with Applications to Probabilistic Time Series Imputationcited by 26
  14. 2019CDSA: Cross-Dimensional Self-Attention for Multivariate, Geo-tagged Time Series Imputationcited by 24
  15. 2023Probabilistic Imputation for Time-series Classification with Missing Datacited by 21
  16. 2023ST-MLP: A Cascaded Spatio-Temporal Linear Framework with Channel-Independence Strategy for Traffic Forecastingcited by 21
  17. 2023PyPOTS: A Python Toolkit for Machine Learning on Partially-Observed Time Seriescited by 12
  18. 2024Beyond Random Missingness: Clinically Rethinking for Healthcare Time Series Imputationcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 16; 2026: 12.

33 papers.

Sort:

By area:

  1. 2025Time-MQA: Time Series Multi-Task Question Answering with Context Enhancementcited by 74
  2. 2024A Picture is Worth A Thousand Numbers: Enabling LLMs Reason about Time Series via Visualizationcited by 31
  3. 2025How Can Time Series Analysis Benefit From Multiple Modalities? A Survey and Outlookcited by 20
  4. 2025Achieving Time Series Reasoning Requires Rethinking Model Design, Tasks Formulation, and Evaluationcited by 15
  5. 2026TSRBench: A Comprehensive Multi-task Multi-modal Time Series Reasoning Benchmark for Generalist Modelscited by 14
  6. 2025When LLM Meets Time Series: Can LLMs Perform Multi-Step Time Series Reasoning and Inferencecited by 12
  7. 2025Can Multimodal LLMs Perform Time Series Anomaly Detection?cited by 11
  8. 2025Evaluating System 1 vs. 2 Reasoning Approaches for Zero-Shot Time Series Forecasting: A Benchmark and Insightscited by 11
  9. 2025Glocal Information Bottleneck for Time Series Imputationcited by 9
  10. 2024Task-oriented Time Series Imputation Evaluation via Generalized Representerscited by 6
  11. 2025TimeRecipe: A Time-Series Forecasting Recipe via Benchmarking Module Level Effectivenesscited by 6
  12. 2024How Deep is your Guess? A Fresh Perspective on Deep Learning for Medical Time-Series Imputationcited by 5
21 more
  1. 2025Cross-Domain Conditional Diffusion Models for Time Series Imputationcited by 4
  2. 2024Intelligent Cross-Organizational Process Mining: A Survey and New Perspectivescited by 2
  3. 2025Bridging Smart Meter Gaps: A Benchmark of Statistical, Machine Learning and Time Series Foundation Models for Data Imputationcited by 2
  4. 2026TSRouter: Dynamic Modality-Model Selection for Time Series Reasoningcited by 2
  5. 2026The Stationarity Bias: Stratified Stress-Testing for Time-Series Imputation in Regulated Dynamical Systemscited by 1
  6. 2026HELIX: Hybrid Encoding with Learnable Identity and Cross-dimensional Synthesis for Time Series Imputationcited by 1
  7. 2024A Survey and Benchmarking of Spatial-Temporal Traffic Data Imputation Modelscited by 0
  8. 2025NeuralPrefix: A Zero-shot Sensory Data Imputation Plugincited by 0
  9. 2025ImputeGAP: A Comprehensive Library for Time Series Imputationcited by 0
  10. 2025Fourier Learning Machines: Nonharmonic Fourier-Based Neural Networks for Scientific Machine Learningcited by 0
  11. 2025Diffusion Transformers for Imputation: Statistical Efficiency and Uncertainty Quantificationcited by 0
  12. 2025An Interdisciplinary and Cross-Task Review on Missing Data Imputationcited by 0
  13. 2025HAGI++: Head-Assisted Gaze Imputation and Generationcited by 0
  14. 2026Analyzing and Improving Diffusion Models for Time-Series Data Imputation: A Proximal Recursion Perspectivecited by 0
  15. 2026SEDformer: Event-Synchronous Spiking Transformers for Irregular Telemetry Time Series Forecastingcited by 0
  16. 2026Uniform Inductive Spatio-Temporal Krigingcited by 0
  17. 2026EVIL: Evolving Interpretable Algorithms for Zero-Shot Inference on Event Sequences and Time Series with LLMscited by 0
  18. 2026Discretizing Continuous Time Series for Imputation with Masked Diffusion Trainingcited by 0
  19. 2026RDDMPI: Residual Denoising Diffusion Model for Probabilistic Multivariate Time Series Imputationcited by 0
  20. 2026GAUDI: Geometry-Aware Diffusion for Calibrated Air-Quality Time-Series Imputationcited by 0
  21. 2026ProCTI: Prototype-Refined Global Conditioning for Diffusion-Based Time Series Imputationcited by 0