mlsanityData to 7 Oct 2026

SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction

arXiv 2106.09305 ↗First posted 17 Jun 2021cs.LG cs.AIcited by 335

Not on the map. Why?

Abstract (arXiv)

One unique property of time series is that the temporal relations are largely preserved after downsampling into two sub-sequences. By taking advantage of this property, we propose a novel neural network architecture that conducts sample convolution and interaction for temporal modeling and forecasting, named SCINet. Specifically, SCINet is a recursive downsample-convolve-interact architecture. In each layer, we use multiple convolutional filters to extract distinct yet valuable temporal features from the downsampled sub-sequences or features. By combining these rich features aggregated from multiple resolutions, SCINet effectively models time series with complex temporal dynamics. Experimental results show that SCINet achieves significant forecasting accuracy improvements over both existing convolutional models and Transformer-based solutions across various real-world time series forecasting datasets. Our codes and data are available at https://github.com/cure-lab/SCINet.

Key facts. Cited by 335 papers in the map (data through 7 Oct 2026). Builds on 23 of its 45 references that are in the map. First posted on arXiv 17 Jun 2021.

Builds on

23 of 45 references.

References · 23

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  4. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  5. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  6. 2020Reformer: The Efficient Transformercited by 1,658
  7. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
  8. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,125
  9. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,004
  10. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 869
  11. 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 820
  12. 2019Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecastingcited by 748
11 more
  1. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 744
  2. 2019Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecastingcited by 606
  3. 2020Adaptive Graph Convolutional Recurrent Network for Traffic Forecastingcited by 525
  4. 2020Time Series Forecasting With Deep Learning: A Surveycited by 457
  5. 2020Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecastingcited by 212
  6. 2019Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecastingcited by 161
  7. 2018Temporal Pattern Attention for Multivariate Time Series Forecastingcited by 125
  8. 2017Conditional Time Series Forecasting with Convolutional Neural Networkscited by 121
  9. 2018Trellis Networks for Sequence Modelingcited by 50
  10. 2021Temporal Latent Auto-Encoder: A Method for Probabilistic Multivariate Time Series Forecastingcited by 32
  11. 2019Temporal-Clustering Invariance in Irregular Healthcare Time Seriescited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 32; 2024: 107; 2025: 109; 2026: 83.

335 papers.

Sort:

By area:

  1. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,400
  2. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 906
  3. 2024Unified Training of Universal Time Series Forecasting Transformerscited by 588
  4. 2024TimeMixer: Decomposable Multiscale Mixing for Time Series Forecastingcited by 333
  5. 2024TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variablescited by 241
  6. 2024Timer: Generative Pre-trained Transformers Are Large Time Series Modelscited by 198
  7. 2024Deep Time Series Models: A Comprehensive Survey and Benchmarkcited by 191
  8. 2023FITS: Modeling Time Series with 10k Parameterscited by 185
  9. 2023TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecastingcited by 170
  10. 2023Frequency-domain MLPs are More Effective Learners in Time Series Forecastingcited by 170
  11. 2024TimeMixer++: A General Time Series Pattern Machine for Universal Predictive Analysiscited by 113
  12. 2024Is Mamba Effective for Time Series Forecasting?cited by 110
38 more
  1. 2023Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlookcited by 109
  2. 2024SparseTSF: Modeling Long-term Time Series Forecasting with 1k Parameterscited by 103
  3. 2024Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecastingcited by 102
  4. 2024CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patternscited by 102
  5. 2024UniTS: A Unified Multi-Task Time Series Modelcited by 93
  6. 2024Timer-XL: Long-Context Transformers for Unified Time Series Forecastingcited by 83
  7. 2024SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time seriescited by 81
  8. 2024FreDF: Learning to Forecast in the Frequency Domaincited by 77
  9. 2024SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusioncited by 75
  10. 2024TSLANet: Rethinking Transformers for Time Series Representation Learningcited by 71
  11. 2024TimeMachine: A Time Series is Worth 4 Mambas for Long-term Forecastingcited by 63
  12. 2023SegRNN: Segment Recurrent Neural Network for Long-Term Time Series Forecastingcited by 53
  13. 2023MTS-Mixers: Multivariate Time Series Forecasting via Factorized Temporal and Channel Mixingcited by 52
  14. 2023TimesURL: Self-supervised Contrastive Learning for Universal Time Series Representation Learningcited by 51
  15. 2024Frequency Adaptive Normalization For Non-stationary Time Series Forecastingcited by 45
  16. 2024Revitalizing Multivariate Time Series Forecasting: Learnable Decomposition with Inter-Series Dependencies and Intra-Series Variations Modelingcited by 44
  17. 2024Toto: Time Series Optimized Transformer for Observabilitycited by 44
  18. 2024FilterNet: Harnessing Frequency Filters for Time Series Forecastingcited by 44
  19. 2024TimeBridge: Non-Stationarity Matters for Long-term Time Series Forecastingcited by 38
  20. 2024TOTEM: TOkenized Time Series EMbeddings for General Time Series Analysiscited by 37
  21. 2024From Similarity to Superiority: Channel Clustering for Time Series Forecastingcited by 37
  22. 2023ProbTS: Benchmarking Point and Distributional Forecasting across Diverse Prediction Horizonscited by 35
  23. 2024Retrieval-Augmented Diffusion Models for Time Series Forecastingcited by 35
  24. 2024Adaptive Multi-Scale Decomposition Framework for Time Series Forecastingcited by 34
  25. 2025Patch-wise Structural Loss for Time Series Forecastingcited by 34
  26. 2024TSI-Bench: Benchmarking Time Series Imputationcited by 33
  27. 2024Towards a General Time Series Forecasting Model with Unified Representation and Adaptive Transfercited by 31
  28. 2025Temporal Query Network for Efficient Multivariate Time Series Forecastingcited by 29
  29. 2025LightGTS: A Lightweight General Time Series Forecasting Modelcited by 28
  30. 2025Aurora: Towards Universal Generative Multimodal Time Series Forecastingcited by 28
  31. 2025TimeKAN: KAN-based Frequency Decomposition Learning Architecture for Long-term Time Series Forecastingcited by 27
  32. 2024Hierarchical Classification Auxiliary Network for Time Series Forecastingcited by 26
  33. 2024WPMixer: Efficient Multi-Resolution Mixing for Long-Term Time Series Forecastingcited by 25
  34. 2025OLinear: A Linear Model for Time Series Forecasting in Orthogonally Transformed Domaincited by 25
  35. 2025Amplifier: Bringing Attention to Neglected Low-Energy Components in Time Series Forecastingcited by 23
  36. 2024RWKV-TS: Beyond Traditional Recurrent Neural Network for Time Series Taskscited by 22
  37. 2025Time-o1: Time-Series Forecasting Needs Transformed Label Alignmentcited by 22
  38. 2024Ada-MSHyper: Adaptive Multi-Scale Hypergraph Transformer for Time Series Forecastingcited by 21

50 most cited of 335 All 335 (JSON)