mlsanityData to 7 Oct 2026

NAOMI: Non-Autoregressive Multiresolution Sequence Imputation

arXiv 1901.10946 ↗First posted 30 Jan 2019cs.LG stat.MLcited by 59

Not on the map. Why?

Abstract (arXiv)

Missing value imputation is a fundamental problem in spatiotemporal modeling, from motion tracking to the dynamics of physical systems. Deep autoregressive models suffer from error propagation which becomes catastrophic for imputing long-range sequences. In this paper, we take a non-autoregressive approach and propose a novel deep generative model: Non-AutOregressive Multiresolution Imputation (NAOMI) to impute long-range sequences given arbitrary missing patterns. NAOMI exploits the multiresolution structure of spatiotemporal data and decodes recursively from coarse to fine-grained resolutions using a divide-and-conquer strategy. We further enhance our model with adversarial training. When evaluated extensively on benchmark datasets from systems of both deterministic and stochastic dynamics. NAOMI demonstrates significant improvement in imputation accuracy (reducing average prediction error by 60% compared to autoregressive counterparts) and generalization for long range sequences.

Key facts. Cited by 59 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Jan 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 11; 2023: 14; 2024: 12; 2025: 11; 2026: 4.

59 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. 2021Filling the G_ap_s: Multivariate Time Series Imputation by Graph Neural Networkscited by 93
  4. 2022Learning to Reconstruct Missing Data from Spatiotemporal Graphs with Sparse Observationscited by 64
  5. 2023PriSTI: A Conditional Diffusion Framework for Spatiotemporal Imputationcited by 62
  6. 2023ImputeFormer: Low Rankness-Induced Transformers for Generalizable Spatiotemporal Imputationcited by 50
  7. 2023Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Predictioncited by 47
  8. 2021Missing Value Imputation on Multidimensional Time Seriescited by 33
  9. 2023Deep Imputation of Missing Values in Time Series Health Data: A Review with Benchmarkingcited by 29
  10. 2021NRTSI: Non-Recurrent Time Series Imputationcited by 25
  11. 2023Time Series Continuous Modeling for Imputation and Forecasting with Implicit Neural Representationscited by 16
  12. 2025Unified Uncertainty-Aware Diffusion for Multi-Agent Trajectory Modelingcited by 15
38 more
  1. 2023Ball Trajectory Inference from Multi-Agent Sports Contexts Using Set Transformer and Hierarchical Bi-LSTMcited by 12
  2. 2024Causality-Aware Spatiotemporal Graph Neural Networks for Spatiotemporal Time Series Imputationcited by 11
  3. 2024TranSPORTmer: A Holistic Approach to Trajectory Understanding in Multi-Agent Sportscited by 11
  4. 2023Joint Sensing, Communication, and AI: A Trifecta for Resilient THz User Experiencescited by 10
  5. 2022Forecasting Unobserved Node States with spatio-temporal Graph Neural Networkscited by 9
  6. 2022PulseImpute: A Novel Benchmark Task for Pulsative Physiological Signal Imputationcited by 9
  7. 2023BayOTIDE: Bayesian Online Multivariate Time series Imputation with functional decompositioncited by 9
  8. 2024Pedestrian Trajectory Prediction with Missing Data: Datasets, Imputation, and Benchmarkingcited by 8
  9. 2021Time-series Imputation of Temporally-occluded Multiagent Trajectoriescited by 7
  10. 2022Taming the Long Tail of Deep Probabilistic Forecastingcited by 7
  11. 2021Data-driven Analysis for Understanding Team Sports Behaviorscited by 6
  12. 2023Improving Diffusion Models for ECG Imputation with an Augmented Template Priorcited by 6
  13. 2023Missing Value Imputation for Multi-attribute Sensor Data Streams via Message Propagation (Extended Version)cited by 6
  14. 2022Deep Neural Imputation: A Framework for Recovering Incomplete Brain Recordingscited by 5
  15. 2024How Deep is your Guess? A Fresh Perspective on Deep Learning for Medical Time-Series Imputationcited by 5
  16. 2025Self-attention-based Diffusion Model for Time-series Imputation in Partial Blackout Scenarioscited by 5
  17. 2025JointDiff: Bridging Continuous and Discrete in Multi-Agent Trajectory Generationcited by 5
  18. 2025EgoTraj-Bench: Towards Robust Trajectory Prediction Under Ego-view Noisy Observationscited by 5
  19. 2022T2FPV: Dataset and Method for Correcting First-Person View Errors in Pedestrian Trajectory Predictioncited by 4
  20. 2024Learnable Prompt as Pseudo-Imputation: Rethinking the Necessity of Traditional EHR Data Imputation in Downstream Clinical Predictioncited by 4
  21. 2024A Temporally Disentangled Contrastive Diffusion Model for Spatiotemporal Imputationcited by 4
  22. 2024NuwaTS: a Foundation Model Mending Every Incomplete Time Seriescited by 4
  23. 2023Multiple-level Point Embedding for Solving Human Trajectory Imputation with Predictioncited by 3
  24. 2024Trajectory Imputation in Multi-Agent Sports with Derivative-Accumulating Self-Ensemblecited by 3
  25. 2024Well log data generation and imputation using sequence-based generative adversarial networkscited by 3
  26. 2026Heteroscedastic Diffusion for Multi-Agent Trajectory Modelingcited by 3
  27. 2021PIETS: Parallelised Irregularity Encoders for Forecasting with Heterogeneous Time-Seriescited by 2
  28. 2021DeepFIB: Self-Imputation for Time Series Anomaly Detectioncited by 2
  29. 2022Probabilistic Symmetry for Multi-Agent Dynamicscited by 2
  30. 2024Machine Learning for Missing Value Imputationcited by 2
  31. 2025Boundary-enhanced time series data imputation with long-term dependency diffusion modelscited by 2
  32. 2025FADTI: Fourier and Attention Driven Diffusion for Multivariate Time Series Imputationcited by 2
  33. 2022SpectraNet: Multivariate Forecasting and Imputation under Distribution Shifts and Missing Datacited by 1
  34. 2023Filling out the missing gaps: Time Series Imputation with Semi-Supervised Learningcited by 1
  35. 2024An End-to-End Model for Time Series Classification In the Presence of Missing Valuescited by 1
  36. 2025Investigating a Model-Agnostic and Imputation-Free Approach for Irregularly-Sampled Multivariate Time-Series Modelingcited by 1
  37. 2025MoTM: Towards a Foundation Model for Time Series Imputation based on Continuous Modelingcited by 1
  38. 2025Multi-Modal Soccer Scene Analysis with Masked Pre-Trainingcited by 1

50 most cited of 59 All 59 (JSON)