mlsanityData to 7 Oct 2026

Temporal Latent Auto-Encoder: A Method for Probabilistic Multivariate Time Series Forecasting

arXiv 2101.10460 ↗First posted 25 Jan 2021cs.LG cs.AI cs.NEcited by 32

Not on the map. Why?

Abstract (arXiv)

Probabilistic forecasting of high dimensional multivariate time series is a notoriously challenging task, both in terms of computational burden and distribution modeling. Most previous work either makes simple distribution assumptions or abandons modeling cross-series correlations. A promising line of work exploits scalable matrix factorization for latent-space forecasting, but is limited to linear embeddings, unable to model distributions, and not trainable end-to-end when using deep learning forecasting. We introduce a novel temporal latent auto-encoder method which enables nonlinear factorization of multivariate time series, learned end-to-end with a temporal deep learning latent space forecast model. By imposing a probabilistic latent space model, complex distributions of the input series are modeled via the decoder. Extensive experiments demonstrate that our model achieves state-of-the-art performance on many popular multivariate datasets, with gains sometimes as high as 50% for several standard metrics.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). Builds on 22 of its 70 references that are in the map. First posted on arXiv 25 Jan 2021.

Builds on

22 of 70 references.

References · 22

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  3. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  4. 2013Auto-Encoding Variational Bayescited by 3,980
  5. 2016Density estimation using Real NVPcited by 2,029
  6. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
  7. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,004
  8. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 869
  9. 2019Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecastingcited by 606
  10. 2016Tutorial on Variational Autoencoderscited by 404
  11. 2015A Recurrent Latent Variable Model for Sequential Datacited by 362
  12. 2017A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Predictioncited by 245
10 more
  1. 2017A Multi-Horizon Quantile Recurrent Forecastercited by 211
  2. 2019Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecastingcited by 161
  3. 2019High-Dimensional Multivariate Forecasting with Low-Rank Gaussian Copula Processescited by 147
  4. 2020Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing Flowscited by 142
  5. 2017Conditional Time Series Forecasting with Convolutional Neural Networkscited by 121
  6. 2019Deep Factors for Forecastingcited by 86
  7. 2018Beyond expectation: Deep joint mean and quantile regression for spatio-temporal problemscited by 32
  8. 2019LSTM-MSNet: Leveraging Forecasts on Sets of Related Time Series with Multiple Seasonal Patternscited by 23
  9. 2019Towards Better Forecasting by Fusing Near and Distant Future Visionscited by 14
  10. 2017R2N2: Residual Recurrent Neural Networks for Multivariate Time Series Forecastingcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 9; 2023: 8; 2024: 7; 2025: 5; 2026: 1.

32 papers.

Sort:

By area:

  1. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 577
  2. 2021SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interactioncited by 335
  3. 2022Diffusion-based Time Series Imputation and Forecasting with Structured State Space Modelscited by 195
  4. 2023Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglementcited by 89
  5. 2023Temporal Data Meets LLM -- Explainable Financial Time Series Forecastingcited by 77
  6. 2022Learning the Evolutionary and Multi-scale Graph Structure for Multivariate Time Series Forecastingcited by 36
  7. 2024The Rise of Diffusion Models in Time-Series Forecastingcited by 25
  8. 2022Decoupling Local and Global Representations of Time Seriescited by 17
  9. 2022Federated Learning for 5G Base Station Traffic Forecastingcited by 15
  10. 2023Towards Long-Term Time-Series Forecasting: Feature, Pattern, and Distributioncited by 15
  11. 2024Self-Supervised Learning of Time Series Representation via Diffusion Process and Imputation-Interpolation-Forecasting Maskcited by 10
  12. 2022Distributional Drift Adaptation with Temporal Conditional Variational Autoencoder for Multivariate Time Series Forecastingcited by 7
20 more
  1. 2023Regions of Reliability in the Evaluation of Multivariate Probabilistic Forecastscited by 7
  2. 2022Probabilistic Decomposition Transformer for Time Series Forecastingcited by 6
  3. 2024Deep Coupling Network For Multivariate Time Series Forecastingcited by 6
  4. 2023Deep Evidential Learning for Bayesian Quantile Regressioncited by 5
  5. 2024A Survey of Transformer Enabled Time Series Synthesiscited by 5
  6. 2022Probabilistic forecasts of wind power generation in regions with complex topography using deep learning methods: An Arctic casecited by 3
  7. 2022Latent Temporal Flows for Multivariate Analysis of Wearables Datacited by 2
  8. 2023Non-parametric Probabilistic Time Series Forecasting via Innovations Representationcited by 2
  9. 2025Neural MJD: Neural Non-Stationary Merton Jump Diffusion for Time Series Predictioncited by 2
  10. 2024Generative Probabilistic Time Series Forecasting and Applications in Grid Operationscited by 1
  11. 2025How to Unlock Time Series Editing? Diffusion-Driven Approach with Multi-Grained Controlcited by 1
  12. 2025PRISM: A hierarchical multiscale approach for time series forecastingcited by 1
  13. 2022DynaConF: Dynamic Forecasting of Non-Stationary Time Seriescited by 0
  14. 2023OrcoDCS: An IoT-Edge Orchestrated Online Deep Compressed Sensing Frameworkcited by 0
  15. 2023Encoding Seasonal Climate Predictions for Demand Forecasting with Modular Neural Networkcited by 0
  16. 2024Unsupervised Representation Learning of Complex Time Series for Maneuverability State Identification in Smart Mobilitycited by 0
  17. 2024The Roles of Generative Artificial Intelligence in Internet of Electric Vehiclescited by 0
  18. 2025CoRe: Coherency Regularization for Hierarchical Time Seriescited by 0
  19. 2025AI Foundation Model for Time Series with Innovations Representationcited by 0
  20. 2026ProbRes: Volatility Learning for Probabilistic Time-Series Forecastingcited by 0