mlsanityData to 14 Oct 2026

Temporal Pattern Attention for Multivariate Time Series Forecasting

arXiv 1809.04206 ↗First posted 12 Sep 2018cs.LG cs.CL stat.MLcited by 125

Not on the map. Why?

Abstract (arXiv)

Forecasting multivariate time series data, such as prediction of electricity consumption, solar power production, and polyphonic piano pieces, has numerous valuable applications. However, complex and non-linear interdependencies between time steps and series complicate the task. To obtain accurate prediction, it is crucial to model long-term dependency in time series data, which can be achieved to some good extent by recurrent neural network (RNN) with attention mechanism. Typical attention mechanism reviews the information at each previous time step and selects the relevant information to help generate the outputs, but it fails to capture the temporal patterns across multiple time steps. In this paper, we propose to use a set of filters to extract time-invariant temporal patterns, which is similar to transforming time series data into its "frequency domain". Then we proposed a novel attention mechanism to select relevant time series, and use its "frequency domain" information for forecasting. We applied the proposed model on several real-world tasks and achieved state-of-the-art performance in all of them with only one exception.

Key facts. Cited by 125 papers in the map (data through 14 Oct 2026). First posted on arXiv 12 Sep 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 24; 2022: 34; 2023: 28; 2024: 14; 2025: 22; 2026: 3.

125 papers.

Sort:

By area:

  1. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  2. 2021SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interactioncited by 338
  3. 2021Discrete Graph Structure Learning for Forecasting Multiple Time Seriescited by 171
  4. 2022Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structurescited by 160
  5. 2023A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detectioncited by 145
  6. 2023Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglementcited by 90
  7. 2022Spatio-Temporal Meta-Graph Learning for Traffic Forecastingcited by 88
  8. 2021DL-Traff: Survey and Benchmark of Deep Learning Models for Urban Traffic Predictioncited by 73
  9. 2022Multivariate Time Series Forecasting with Dynamic Graph Neural ODEscited by 72
  10. 2022Forecast Evaluation for Data Scientists: Common Pitfalls and Best Practicescited by 55
  11. 2024A Temporal Kolmogorov-Arnold Transformer for Time Series Forecastingcited by 52
  12. 2021AutoCTS: Automated Correlated Time Series Forecasting -- Extended Versioncited by 48
38 more
  1. 2021Long-Range Transformers for Dynamic Spatiotemporal Forecastingcited by 46
  2. 2023TimeMAE: Self-Supervised Representations of Time Series with Decoupled Masked Autoencoderscited by 44
  3. 2021ScoreGrad: Multivariate Probabilistic Time Series Forecasting with Continuous Energy-based Generative Modelscited by 43
  4. 2022Multi-Scale Adaptive Graph Neural Network for Multivariate Time Series Forecastingcited by 42
  5. 2022TACTiS: Transformer-Attentional Copulas for Time Seriescited by 38
  6. 2022Learning the Evolutionary and Multi-scale Graph Structure for Multivariate Time Series Forecastingcited by 36
  7. 2021Historical Inertia: A Neglected but Powerful Baseline for Long Sequence Time-series Forecastingcited by 26
  8. 2023TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Seriescited by 26
  9. 2021Merlion: A Machine Learning Library for Time Seriescited by 25
  10. 2021Spatio-temporal graph neural networks for multi-site PV power forecastingcited by 24
  11. 2022Joint Neural Architecture and Hyperparameter Search for Correlated Time Series Forecastingcited by 22
  12. 2022Multivariate Time Series Forecasting with Latent Graph Inferencecited by 20
  13. 2023NuTime: Numerically Multi-Scaled Embedding for Large-Scale Time-Series Pretrainingcited by 20
  14. 2022Multi-scale Attention Flow for Probabilistic Time Series Forecastingcited by 19
  15. 2021Adjusting for Autocorrelated Errors in Neural Networks for Time Seriescited by 18
  16. 2023LightCTS: A Lightweight Framework for Correlated Time Series Forecastingcited by 18
  17. 2022EpiGNN: Exploring Spatial Transmission with Graph Neural Network for Regional Epidemic Forecastingcited by 17
  18. 2023pTSE: A Multi-model Ensemble Method for Probabilistic Time Series Forecastingcited by 16
  19. 2023Traffic Prediction using Artificial Intelligence: Review of Recent Advances and Emerging Opportunitiescited by 16
  20. 2025PPGF: Probability Pattern-Guided Time Series Forecastingcited by 16
  21. 2025Positional Encoding in Transformer-Based Time Series Models: A Surveycited by 14
  22. 2024Fully Automated Correlated Time Series Forecasting in Minutescited by 12
  23. 2021Towards a Rigorous Evaluation of Explainability for Multivariate Time Seriescited by 10
  24. 2021From Known to Unknown: Knowledge-guided Transformer for Time-Series Sales Forecasting in Alibabacited by 10
  25. 2023Counterfactual Explanations for Time Series Forecastingcited by 10
  26. 2021Scale-Aware Neural Architecture Search for Multivariate Time Series Forecastingcited by 9
  27. 2023Multi-scale Transformer Pyramid Networks for Multivariate Time Series Forecastingcited by 9
  28. 2023A physics-informed and attention-based graph learning approach for regional electric vehicle charging demand predictioncited by 9
  29. 2024Towards a Digital Twin Framework in Additive Manufacturing: Machine Learning and Bayesian Optimization for Time Series Process Optimizationcited by 9
  30. 2024A Systematic Literature Review of Spatio-Temporal Graph Neural Network Models for Time Series Forecasting and Classificationcited by 9
  31. 2023Learning Informative Representation for Fairness-aware Multivariate Time-series Forecasting: A Group-based Perspectivecited by 8
  32. 2021TENT: Tensorized Encoder Transformer for Temperature Forecastingcited by 7
  33. 2022Distributional Drift Adaptation with Temporal Conditional Variational Autoencoder for Multivariate Time Series Forecastingcited by 7
  34. 2022Learning Differential Operators for Interpretable Time Series Modelingcited by 7
  35. 2023MemDA: Forecasting Urban Time Series with Memory-based Drift Adaptationcited by 7
  36. 2022FreDo: Frequency Domain-based Long-Term Time Series Forecastingcited by 6
  37. 2023ARM: Refining Multivariate Forecasting with Adaptive Temporal-Contextual Learningcited by 6
  38. 2024Multivariate Probabilistic Time Series Forecasting with Correlated Errorscited by 6

50 most cited of 125 All 125 (JSON)