mlsanityData to 14 Oct 2026

Learning Deep Time-index Models for Time Series Forecasting

arXiv 2207.06046 ↗First posted 13 Jul 2022cs.LG cs.AIcited by 18

Not on the map. Why?

Abstract (arXiv)

Deep learning has been actively applied to time series forecasting, leading to a deluge of new methods, belonging to the class of historical-value models. Yet, despite the attractive properties of time-index models, such as being able to model the continuous nature of underlying time series dynamics, little attention has been given to them. Indeed, while naive deep time-index models are far more expressive than the manually predefined function representations of classical time-index models, they are inadequate for forecasting, being unable to generalize to unseen time steps due to the lack of inductive bias. In this paper, we propose DeepTime, a meta-optimization framework to learn deep time-index models which overcome these limitations, yielding an efficient and accurate forecasting model. Extensive experiments on real world datasets in the long sequence time-series forecasting setting demonstrate that our approach achieves competitive results with state-of-the-art methods, and is highly efficient. Code is available at https://github.com/salesforce/DeepTime.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Builds on 31 of its 64 references that are in the map. First posted on arXiv 13 Jul 2022.

Builds on

31 of 64 references.

References · 31

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016Layer Normalizationcited by 5,669
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  4. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  5. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  6. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  7. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  8. 2018On the Spectral Bias of Neural Networkscited by 1,341
  9. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,210
  10. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,013
  11. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 879
  12. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 753
19 more
  1. 2019Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecastingcited by 607
  2. 2018Meta-learning with differentiable closed-form solverscited by 397
  3. 2022Non-stationary Transformers: Exploring the Stationarity in Time Series Forecastingcited by 391
  4. 2021Advances in Neural Renderingcited by 365
  5. 2018How to train your MAMLcited by 309
  6. 2020Learned Initializations for Optimizing Coordinate-Based Neural Representationscited by 242
  7. 2020MetaSDF: Meta-learning Signed Distance Functionscited by 214
  8. 2022ETSformer: Exponential Smoothing Transformers for Time-series Forecastingcited by 148
  9. 2022N-HiTS: Neural Hierarchical Interpolation for Time Series Forecastingcited by 146
  10. 2020Frequency Bias in Neural Networks for Input of Non-Uniform Densitycited by 140
  11. 2021A Structured Dictionary Perspective on Implicit Neural Representationscited by 100
  12. 2019Meta-Learning without Memorizationcited by 92
  13. 2021Generative Models as Distributions of Functionscited by 89
  14. 2017Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theorycited by 76
  15. 2020Meta-Learning Requires Meta-Augmentationcited by 57
  16. 2020Time series forecasting with Gaussian Processes needs priorscited by 13
  17. 2022Time-Series Anomaly Detection with Implicit Neural Representationcited by 10
  18. 2017Neural Decomposition of Time-Series Data for Effective Generalizationcited by 9
  19. 2021Meta-Forecasting by combining Global Deep Representations with Local Adaptationcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 8; 2025: 5; 2026: 1.

18 papers.

Sort:

  1. 2024Kolmogorov-Arnold Networks for Time Series: Bridging Predictive Power and Interpretabilitycited by 70
  2. 2023A Survey on Deep Learning based Time Series Analysis with Frequency Transformationcited by 40
  3. 2023Pushing the Limits of Pre-training for Time Series Forecasting in the CloudOps Domaincited by 23
  4. 2024Are Self-Attentions Effective for Time Series Forecasting?cited by 19
  5. 2024Quantum Implicit Neural Representationscited by 16
  6. 2024Spatiotemporal Implicit Neural Representation as a Generalized Traffic Data Learnercited by 7
  7. 2023A Joint Time-frequency Domain Transformer for Multivariate Time Series Forecastingcited by 5
  8. 2026TS-ICL: A Flexible Time-Indexed Foundation Model for Time Series via In-Context Learningcited by 4
  9. 2024Partial-Multivariate Model for Forecastingcited by 2
  10. 2022DynaConF: Dynamic Forecasting of Non-Stationary Time Seriescited by 1
  11. 2024PDETime: Rethinking Long-Term Multivariate Time Series Forecasting from the perspective of partial differential equationscited by 1
  12. 2024Robust Multivariate Time Series Forecasting against Intra- and Inter-Series Transitional Shiftcited by 1
6 more
  1. 2025Temporal Variational Implicit Neural Representationscited by 1
  2. 2025MoTM: Towards a Foundation Model for Time Series Imputation based on Continuous Modelingcited by 1
  3. 2025Are Time-Indexed Foundation Models the Future of Time Series Imputation?cited by 1
  4. 2024Variational quantization for state space modelscited by 0
  5. 2025Collaborative Imputation of Urban Time Series through Cross-city Meta-learningcited by 0
  6. 2025iADCPS: Time Series Anomaly Detection for Evolving Cyber-physical Systems via Incremental Meta-learningcited by 0