mlsanityData to 7 Oct 2026

Multi-resolution Time-Series Transformer for Long-term Forecasting

arXiv 2311.04147 ↗First posted 7 Nov 2023cs.LGcited by 41

Not on the map. Why?

Abstract (arXiv)

The performance of transformers for time-series forecasting has improved significantly. Recent architectures learn complex temporal patterns by segmenting a time-series into patches and using the patches as tokens. The patch size controls the ability of transformers to learn the temporal patterns at different frequencies: shorter patches are effective for learning localized, high-frequency patterns, whereas mining long-term seasonalities and trends requires longer patches. Inspired by this observation, we propose a novel framework, Multi-resolution Time-Series Transformer (MTST), which consists of a multi-branch architecture for simultaneous modeling of diverse temporal patterns at different resolutions. In contrast to many existing time-series transformers, we employ relative positional encoding, which is better suited for extracting periodic components at different scales. Extensive experiments on several real-world datasets demonstrate the effectiveness of MTST in comparison to state-of-the-art forecasting techniques.

Key facts. Cited by 41 papers in the map (data through 7 Oct 2026). Builds on 32 of its 44 references that are in the map. First posted on arXiv 7 Nov 2023.

Builds on

32 of 44 references.

References · 32

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  7. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  8. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  9. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  10. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  11. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 1,981
  12. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
20 more
  1. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,830
  2. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,654
  3. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
  4. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,400
  5. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,200
  6. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,128
  7. 2018Self-Attention with Relative Position Representationscited by 1,112
  8. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,030
  9. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,004
  10. 2022Token Merging: Your ViT But Fastercited by 995
  11. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 869
  12. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 744
  13. 2019Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecastingcited by 606
  14. 2017A Multi-Horizon Quantile Recurrent Forecastercited by 211
  15. 2018Music Transformercited by 207
  16. 2019Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecastingcited by 161
  17. 2022N-HiTS: Neural Hierarchical Interpolation for Time Series Forecastingcited by 146
  18. 2023TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecastingcited by 136
  19. 2016Multi-Scale Convolutional Neural Networks for Time Series Classificationcited by 99
  20. 2022Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecastingcited by 54

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 22; 2026: 12.

41 papers.

Sort:

By area:

  1. 2024Medformer: A Multi-Granularity Patching Transformer for Medical Time-Series Classificationcited by 53
  2. 2025Foundation Models for Time Series: A Surveycited by 19
  3. 2024SST: Multi-Scale Hybrid Mamba-Transformer Experts for Time Series Forecastingcited by 15
  4. 2025Multi-Scale Finetuning for Encoder-based Time Series Foundation Modelscited by 13
  5. 2024ElasTST: Towards Robust Varied-Horizon Forecasting with Elastic Time-Series Transformercited by 10
  6. 2025AttenGluco: Multimodal Transformer-Based Blood Glucose Forecasting on AI-READI Datasetcited by 9
  7. 2024Repurposing Foundation Model for Generalizable Medical Time Series Classificationcited by 6
  8. 2026Decentralized Attention Fails Centralized Signals: Rethinking Transformers for Medical Time Seriescited by 5
  9. 2025Not All Data are Good Labels: On the Self-supervised Labeling for Time Series Forecastingcited by 4
  10. 2024QuLTSF: Long-Term Time Series Forecasting with Quantum Machine Learningcited by 3
  11. 2026Universal Redundancies in Time Series Foundation Modelscited by 3
  12. 2025MedSpaformer: a Transferable Transformer with Multi-granularity Token Sparsification for Medical Time Series Classificationcited by 2
29 more
  1. 2025Plain Transformers Can be Powerful Graph Learnerscited by 2
  2. 2024InjectTST: A Transformer Method of Injecting Global Information into Independent Channels for Long Time Series Forecastingcited by 1
  3. 2024Multiple-Resolution Tokenization for Time Series Forecasting with an Application to Pricingcited by 1
  4. 2025Cardioformer: Advancing AI in ECG Analysis with Multi-Granularity Patching and ResNetcited by 1
  5. 2025A Dynamic Stiefel Graph Neural Network for Efficient Spatio-Temporal Time Series Forecastingcited by 1
  6. 2025SKOLR: Structured Koopman Operator Linear RNN for Time-Series Forecastingcited by 1
  7. 2025SEED: A Structural Encoder for Embedding-Driven Decoding in Time Series Prediction with LLMscited by 1
  8. 2025CoSupFormer : A Contrastive Supervised learning approach for EEG signal Classificationcited by 1
  9. 2025Hydra: Dual Exponentiated Memory for Multivariate Time Series Analysiscited by 1
  10. 2025Energy-Aware Pattern Disentanglement: A Generalizable Pattern Assisted Architecture for Multi-task Time Series Analysiscited by 0
  11. 2025CANet: ChronoAdaptive Network for Enhanced Long-Term Time Series Forecasting under Non-Stationaritycited by 0
  12. 2025Logo-LLM: Local and Global Modeling with Large Language Models for Time Series Forecastingcited by 0
  13. 2025Channel-Imposed Fusion: A Simple yet Effective Method for Medical Time Series Classificationcited by 0
  14. 2025Multivariate Long-term Time Series Forecasting with Fourier Neural Filtercited by 0
  15. 2025IEFS-GMB: Gradient Memory Bank-Guided Feature Selection Based on Information Entropy for EEG Classification of Neurological Disorderscited by 0
  16. 2025M3ET: Efficient Vision-Language Learning for Robotics based on Multimodal Mamba-Enhanced Transformercited by 0
  17. 2025InvDec: Inverted Decoder for Multivariate Time Series Forecasting with Separated Temporal and Variate Modelingcited by 0
  18. 2025Cisco Time Series Model Technical Reportcited by 0
  19. 2025MSTN: A Lightweight and Fast Model for General TimeSeries Analysiscited by 0
  20. 2026Deep Time-Series Forecasting in 10 Years: A Surveycited by 0
  21. 2026Learning Fingerprints for Medical Time Series with Redundancy-Constrained Information Maximizationcited by 0
  22. 2026A Multi-Head Attention Approach for SLA Compliance Monitoring in Data Centerscited by 0
  23. 2026Spectral Transformer Neural Processescited by 0
  24. 2026On What We Can Learn from Low-Resolution Datacited by 0
  25. 2026BioFormer: Rethinking Cross-Subject Generalization via Spectral Structural Alignment in Biomedical Time-Seriescited by 0
  26. 2026TS-Fault: Benchmarking Time Series Forecasters Against Structural Faultscited by 0
  27. 2026Liquid Gated Attentioncited by 0
  28. 2026Revitalizing Medical Time Series with Vision-Informed Retrieval: A Vision-Language Perspectivecited by 0
  29. 2026No Scale Left Behind: Multi-Scale Autoencoder with Bi-directional Attention for Time Series Anomaly Detectioncited by 0