mlsanityData to 14 Oct 2026

Multi-scale Attention Flow for Probabilistic Time Series Forecasting

arXiv 2205.07493 ↗First posted 16 May 2022cs.LGcited by 19

Not on the map. Why?

Abstract (arXiv)

The probability prediction of multivariate time series is a notoriously challenging but practical task. On the one hand, the challenge is how to effectively capture the cross-series correlations between interacting time series, to achieve accurate distribution modeling. On the other hand, we should consider how to capture the contextual information within time series more accurately to model multivariate temporal dynamics of time series. In this work, we proposed a novel non-autoregressive deep learning model, called Multi-scale Attention Normalizing Flow(MANF), where we integrate multi-scale attention and relative position information and the multivariate data distribution is represented by the conditioned normalizing flow. Additionally, compared with autoregressive modeling methods, our model avoids the influence of cumulative error and does not increase the time complexity. Extensive experiments demonstrate that our model achieves state-of-the-art performance on many popular multivariate datasets.

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). Builds on 36 of its 71 references that are in the map. First posted on arXiv 16 May 2022.

Builds on

36 of 71 references.

References · 36

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  5. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  6. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  7. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  8. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  9. 2016Density estimation using Real NVPcited by 2,042
  10. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,850
  11. 2020Big Bird: Transformers for Longer Sequencescited by 1,684
  12. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
24 more
  1. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,323
  2. 2014NICE: Non-linear Independent Components Estimationcited by 1,058
  3. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,013
  4. 2019An Introduction to Variational Autoencoderscited by 1,000
  5. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 879
  6. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 753
  7. 2016Temporal Convolutional Networks for Action Segmentation and Detectioncited by 508
  8. 2021Spectral Temporal Graph Neural Network for Multivariate Time-series Forecastingcited by 299
  9. 2015A note on the evaluation of generative modelscited by 292
  10. 2019Financial Time Series Forecasting with Deep Learning : A Systematic Literature Review: 2005-2019cited by 273
  11. 2019Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Designcited by 262
  12. 2016Structured Inference Networks for Nonlinear State Space Modelscited by 182
  13. 2019Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecastingcited by 161
  14. 2020Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing Flowscited by 144
  15. 2017PixelSNAIL: An Improved Autoregressive Generative Modelcited by 137
  16. 2018Temporal Pattern Attention for Multivariate Time Series Forecastingcited by 125
  17. 2021CTNet: Context-based Tandem Network for Semantic Segmentationcited by 43
  18. 2019Particle Filter Recurrent Neural Networkscited by 36
  19. 2018Beyond expectation: Deep joint mean and quantile regression for spatio-temporal problemscited by 32
  20. 2021Learning Interpretable Deep State Space Model for Probabilistic Time Series Forecastingcited by 29
  21. 2018Transformation Autoregressive Networkscited by 27
  22. 2019Towards Better Forecasting by Fusing Near and Distant Future Visionscited by 14
  23. 2019Deep Semantic Multimodal Hashing Network for Scalable Image-Text and Video-Text Retrievalscited by 8
  24. 2020Parallel Extraction of Long-term Trends and Short-term Fluctuation Framework for Multivariate Time Series Forecastingcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 3; 2024: 5; 2025: 6; 2026: 2.

19 papers.

Sort:

By area:

  1. 2022Detecting Multivariate Time Series Anomalies with Zero Known Labelcited by 21
  2. 2023Label-Free Multivariate Time Series Anomaly Detectioncited by 14
  3. 2022W-Transformers : A Wavelet-based Transformer Framework for Univariate Time Series Forecastingcited by 12
  4. 2023Hierarchical Skeleton Meta-Prototype Contrastive Learning with Hard Skeleton Mining for Unsupervised Person Re-Identificationcited by 9
  5. 2025Multimodal Conditioned Diffusive Time Series Forecastingcited by 9
  6. 2025K2VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecastingcited by 8
  7. 2024Modeling Temporal Dependencies within the Target for Long-Term Time Series Forecastingcited by 6
  8. 2024Physics-Informed Real NVP for Satellite Power System Fault Detectioncited by 4
  9. 2024ContextFlow++: Generalist-Specialist Flow-based Generative Models with Mixed-Variable Context Encodingcited by 3
  10. 2024UmambaTSF: A U-shaped Multi-Scale Long-Term Time Series Forecasting Method Using Mambacited by 3
  11. 2025MSDformer: Multi-scale Discrete Transformer For Time Series Generationcited by 3
  12. 2025Beyond All-to-All: Causal-Aligned Transformer with Dynamic Structure Learning for Multivariate Time Series Forecastingcited by 1
7 more
  1. 2022Knowledge-based Deep Learning for Modeling Chaotic Systemscited by 0
  2. 2023Probabilistic Learning of Multivariate Time Series with Temporal Irregularitycited by 0
  3. 2024MGCP: A Multi-Grained Correlation based Prediction Network for Multivariate Time Seriescited by 0
  4. 2025Interpretable deep convolutional model for nonlinear multivariate time series in complex systemscited by 0
  5. 2025GluMind: Multimodal Parallel Attention and Knowledge Retention for Robust Cross-Population Blood Glucose Forecastingcited by 0
  6. 2026Beyond Static Uncertainty: Modeling Temporal Uncertainty Dynamics for Probabilistic Time Series Forecastingcited by 0
  7. 2026ProbRes: Volatility Learning for Probabilistic Time-Series Forecastingcited by 0