mlsanityData to 13 Oct 2026

K2VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecasting

arXiv 2505.23017 ↗First posted 29 May 2025cs.LG cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

Probabilistic Time Series Forecasting (PTSF) plays a crucial role in decision-making across various fields, including economics, energy, and transportation. Most existing methods excell at short-term forecasting, while overlooking the hurdles of Long-term Probabilistic Time Series Forecasting (LPTSF). As the forecast horizon extends, the inherent nonlinear dynamics have a significant adverse effect on prediction accuracy, and make generative models inefficient by increasing the cost of each iteration. To overcome these limitations, we introduce K2VAE, an efficient VAE-based generative model that leverages a KoopmanNet to transform nonlinear time series into a linear dynamical system, and devises a KalmanNet to refine predictions and model uncertainty in such linear system, which reduces error accumulation in long-term forecasting. Extensive experiments demonstrate that K2VAE outperforms state-of-the-art methods in both short- and long-term PTSF, providing a more efficient and accurate solution.

Key facts. Cited by 8 papers in the map (data through 13 Oct 2026). Builds on 67 of its 113 references that are in the map. First posted on arXiv 29 May 2025.

Builds on

67 of 113 references.

References · 67

  1. 2017Attention Is All You Needcited by 60,106
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,223
  3. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,143
  4. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,157
  5. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,016
  6. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,413
  7. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,043
  8. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,008
  9. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 918
  10. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 579
  11. 2019Financial Time Series Forecasting with Deep Learning : A Systematic Literature Review: 2005-2019cited by 273
  12. 2021Monash Time Series Forecasting Archivecited by 261
38 more
  1. 2024TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methodscited by 248
  2. 2023FITS: Modeling Time Series with 10k Parameterscited by 190
  3. 2020Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing Flowscited by 143
  4. 2021TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generationcited by 141
  5. 2016Variational Autoencoder for Deep Learning of Images, Labels and Captionscited by 137
  6. 2023Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictorscited by 112
  7. 2024CALF: Aligning LLMs for Time Series Forecasting via Cross-modal Fine-Tuningcited by 107
  8. 2024SparseTSF: Modeling Long-term Time Series Forecasting with 1k Parameterscited by 104
  9. 2024CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patternscited by 104
  10. 2024TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignmentcited by 103
  11. 2024CATCH: Channel-Aware multivariate Time Series Anomaly Detection via Frequency Patchingcited by 93
  12. 2023Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglementcited by 89
  13. 2023Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecastingcited by 86
  14. 2024Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Surveycited by 82
  15. 2022DGraph: A Large-Scale Financial Dataset for Graph Anomaly Detectioncited by 63
  16. 2025TimeFilter: Patch-Specific Spatial-Temporal Graph Filtration for Time Series Forecastingcited by 63
  17. 2022Towards Spatio-Temporal Aware Traffic Time Series Forecasting--Full Versioncited by 59
  18. 2025A Comprehensive Survey of Deep Learning for Multivariate Time Series Forecasting: A Channel Strategy Perspectivecited by 58
  19. 2023LightTS: Lightweight Time Series Classification with Adaptive Ensemble Distillation -- Extended Versioncited by 50
  20. 2023DSformer: A Double Sampling Transformer for Multivariate Time Series Long-term Predictioncited by 49
  21. 2023Causal Recurrent Variational Autoencoder for Medical Time Series Generationcited by 45
  22. 2021Unsupervised Path Representation Learning with Curriculum Negative Samplingcited by 42
  23. 2025SCORE: Story Coherence and Retrieval Enhancement for AI Narrativescited by 42
  24. 2024A Unified Replay-based Continuous Learning Framework for Spatio-Temporal Prediction on Streaming Datacited by 39
  25. 2024TimeBridge: Non-Stationarity Matters for Long-term Time Series Forecastingcited by 38
  26. 2023ProbTS: Benchmarking Point and Distributional Forecasting across Diverse Prediction Horizonscited by 36
  27. 2021Unsupervised Time Series Outlier Detection with Diversity-Driven Convolutional Ensembles -- Extended Versioncited by 35
  28. 2024Adaptive Multi-Scale Decomposition Framework for Time Series Forecastingcited by 34
  29. 2024Towards a General Time Series Forecasting Model with Unified Representation and Adaptive Transfercited by 32
  30. 2024EasyTime: Time Series Forecasting Made Easycited by 30
  31. 2021Learning Interpretable Deep State Space Model for Probabilistic Time Series Forecastingcited by 29
  32. 2024Distilling Semantic Priors from SAM to Efficient Image Restoration Modelscited by 25
  33. 2024Revisiting VAE for Unsupervised Time Series Anomaly Detection: A Frequency Perspectivecited by 23
  34. 2022Joint Neural Architecture and Hyperparameter Search for Correlated Time Series Forecastingcited by 22
  35. 2024GinAR: An End-To-End Multivariate Time Series Forecasting Model Suitable for Variable Missingcited by 20
  36. 2022Multi-scale Attention Flow for Probabilistic Time Series Forecastingcited by 19
  37. 2024GIM: A Million-scale Benchmark for Generative Image Manipulation Detection and Localizationcited by 19
  38. 2024MultiRC: Joint Learning for Time Series Anomaly Prediction and Detection with Multi-scale Reconstructive Contrastcited by 19

50 most cited of 67 All 67 (JSON)

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2025: 3; 2026: 5.

8 papers.

  1. 2025LightGTS: A Lightweight General Time Series Forecasting Modelcited by 29
  2. 2025DistDF: Time-Series Forecasting Needs Joint-Distribution Wasserstein Alignmentcited by 13
  3. 2025Quadratic Direct Forecast for Training Multi-Step Time-Series Forecast Modelscited by 10
  4. 2026Deep Time-Series Forecasting in 10 Years: A Surveycited by 0
  5. 2026CLaST: Context-aware Contrastive VAE for Probabilistic Time Series Forecastingcited by 0
  6. 2026DecoVAE: a Lightweight Interpretable Trend-Seasonal VAE Framework for Efficient Probabilistic Time Series Forecastingcited by 0
  7. 2026Correct then Forecast: Observer State-Space Models for Time Series Forecastingcited by 0
  8. 2026Differentiable Koopman Operator for Contrastive Learning on Dynamic Graphscited by 0