mlsanityData to 14 Oct 2026

Super-Linear: A Lightweight Pretrained Mixture of Linear Experts for Time Series Forecasting

arXiv 2509.15105 ↗First posted 18 Sep 2025cs.LGcited by 2

On the map: Mixture-of-experts → MoE for time series and graphs

Abstract (arXiv)

Time series forecasting (TSF) is critical in domains like energy, finance, healthcare, and logistics, requiring models that generalize across diverse datasets. Large pre-trained models such as Chronos and Time-MoE show strong zero-shot (ZS) performance but suffer from high computational costs. In this work, we introduce Super-Linear, a lightweight and scalable mixture-of-experts (MoE) model for general forecasting. It replaces deep architectures with simple frequency-specialized linear experts, trained on resampled data across multiple frequency regimes. A lightweight spectral gating mechanism dynamically selects relevant experts, enabling efficient, accurate forecasting. Despite its simplicity, Super-Linear demonstrates strong performance across benchmarks, while substantially improving efficiency, robustness to sampling rates, and interpretability. The implementation of Super-Linear is available at: hrefhttps://github.com/azencot-group/SuperLinearhttps://github.com/azencot-group/SuperLinear.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in MoE for time series and graphs, one of 12 directions in Mixture-of-experts. Builds on 52 of its 64 references that are in the map. First posted on arXiv 18 Sep 2025.

Builds on

52 of 64 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025FreqMoE: Enhancing Time Series Forecasting through Frequency Decomposition Mixture of Experts25 Jan
  2. 2024Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts24 Sep

Other references · 50

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  5. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  6. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  7. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  8. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
  9. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,210
  10. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,058
  11. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,013
  12. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 931
38 more
  1. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 879
  2. 2019Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecastingcited by 761
  3. 2024Chronos: Learning the Language of Time Seriescited by 759
  4. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 700
  5. 2023A decoder-only foundation model for time-series forecastingcited by 692
  6. 2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 632
  7. 2024Unified Training of Universal Time Series Forecasting Transformerscited by 614
  8. 2024MOMENT: A Family of Open Time-series Foundation Modelscited by 482
  9. 2023A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPTcited by 368
  10. 2021SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interactioncited by 338
  11. 2021Monash Time Series Forecasting Archivecited by 267
  12. 2024Foundation Models for Time Series Analysis: A Tutorial and Surveycited by 239
  13. 2024GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluationcited by 212
  14. 2024Timer: Generative Pre-trained Transformers Are Large Time Series Modelscited by 208
  15. 2023FITS: Modeling Time Series with 10k Parameterscited by 195
  16. 2025Sundial: A Family of Highly Capable Time Series Foundation Modelscited by 180
  17. 2023TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecastingcited by 174
  18. 2022N-HiTS: Neural Hierarchical Interpolation for Time Series Forecastingcited by 146
  19. 2022CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecastingcited by 144
  20. 2023UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecastingcited by 144
  21. 2024Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Seriescited by 127
  22. 2025TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learningcited by 120
  23. 2024SparseTSF: Modeling Long-term Time Series Forecasting with 1k Parameterscited by 107
  24. 2024DUET: Dual Clustering Enhanced Multivariate Time Series Forecastingcited by 107
  25. 2024CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patternscited by 106
  26. 2024TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignmentcited by 103
  27. 2024VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasterscited by 88
  28. 2024Timer-XL: Long-Context Transformers for Unified Time Series Forecastingcited by 87
  29. 2025Time-VLM: Exploring Multimodal Vision-Language Models for Augmented Time Series Forecastingcited by 63
  30. 2024An Analysis of Linear Time Series Forecasting Modelscited by 41
  31. 2024Towards a General Time Series Forecasting Model with Unified Representation and Adaptive Transfercited by 32
  32. 2020A machine learning approach for forecasting hierarchical time seriescited by 29
  33. 2023Mixture-of-Linear-Experts for Long-term Time Series Forecastingcited by 29
  34. 2023AutoMixer for Improved Multivariate Time-Series Forecasting on Business and IT Observability Datacited by 17
  35. 2024UniTST: Effectively Modeling Inter-Series and Intra-Series Dependencies for Multivariate Time Series Forecastingcited by 13
  36. 2025A Multi-Task Learning Approach to Linear Multivariate Forecastingcited by 3
  37. 2025Tailored Forecasting from Short Time Series via Meta-learningcited by 2
  38. 2024KEDformer:Knowledge Extraction Seasonal Trend Decomposition for Long-term Sequence Predictioncited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Reverso: Efficient Time Series Foundation Models for Zero-shot Forecastingcited by 13
  2. 2026XCTFormer: Leveraging Cross-Channel and Cross-Time Dependencies for Enhanced Time-Series Analysiscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025GateTS: Versatile and Efficient Forecasting via Attention-Inspired routed Mixture-of-Experts
  2. 2026Fast Training of Mixture-of-Experts for Time Series Forecasting via Expert Loss Integration
  3. 2026ASGMamba: Adaptive Spectral Gating Mamba for Multivariate Time Series Forecasting
  4. 2025MoFE-Time: Mixture of Frequency Domain Experts for Time-Series Forecasting Models
  5. 2026Seg-MoE: Multi-Resolution Segment-wise Mixture-of-Experts for Time Series Forecasting Transformers
  6. 2026AME-TS: Anchored Mixture-of-Experts for Time Series Forecasting
  7. 2025Ada-MoGE: Adaptive Mixture of Gaussian Expert Model for Time Series Forecasting
  8. 2025Wavelet Mixture of Experts for Time Series Forecasting