mlsanityData to 14 Oct 2026

Time-o1: Time-Series Forecasting Needs Transformed Label Alignment

arXiv 2505.17847 ↗First posted 23 May 2025cs.LG cs.AI cs.SYcited by 22

Not on the map. Why?

Abstract (arXiv)

Training time-series forecasting models poses unique challenges in loss function design. Most existing approaches adopt temporal mean squared error, but this study reveals two critical limitations: (1) it ignores the presence of label autocorrelation, which biases it from the true label sequence likelihood; (2) it involves excessive number of tasks, which complicates optimization, especially for long-term forecasting. To address these issues, we introduce Time-o1, a transform-enhanced loss function for time-series forecasting. The central idea is to transform the label sequence into decorrelated components with discriminated significance. Models are then trained to align the most significant components, thereby effectively mitigating label autocorrelation and reducing task amount. Experiments demonstrate that Time-o1 achieves state-of-the-art performance and is compatible with various forecast models. Code is available at https://github.com/Master-PLC/Time-o1.

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). Builds on 42 of its 81 references that are in the map. First posted on arXiv 23 May 2025.

Builds on

42 of 81 references.

References · 42

  1. 2017Attention Is All You Needcited by 60,361
  2. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  3. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  4. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  5. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  6. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  7. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
  8. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,210
  9. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,058
  10. 2017A Survey on Multi-Task Learningcited by 840
  11. 2022Transformers in Time Series: A Surveycited by 497
  12. 2021Conflict-Averse Gradient Descent for Multi-task Learningcited by 459
30 more
  1. 2024TimeMixer: Decomposable Multiscale Mixing for Time Series Forecastingcited by 346
  2. 2021SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interactioncited by 338
  3. 2023Long-term Forecasting with TiDE: Time-series Dense Encodercited by 332
  4. 2021Spectral Temporal Graph Neural Network for Multivariate Time-series Forecastingcited by 299
  5. 2017Soft-DTW: a Differentiable Loss Function for Time-Seriescited by 271
  6. 2024TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methodscited by 249
  7. 2024Deep Time Series Models: A Comprehensive Survey and Benchmarkcited by 197
  8. 2023FITS: Modeling Time Series with 10k Parameterscited by 195
  9. 2023Frequency-domain MLPs are More Effective Learners in Time Series Forecastingcited by 172
  10. 2023FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspectivecited by 127
  11. 2018Connecting the Dots: Identifying Network Structure via Graph Signal Processingcited by 111
  12. 2024DUET: Dual Clustering Enhanced Multivariate Time Series Forecastingcited by 107
  13. 2024FreDF: Learning to Forecast in the Frequency Domaincited by 79
  14. 2019Shape and Time Distortion Loss for Training Deep Time Series Forecasting Modelscited by 70
  15. 2024TSFM-Bench: A Comprehensive and Unified Benchmark of Foundation Models for Time Series Forecastingcited by 58
  16. 2020From Fourier to Koopman: Spectral Methods for Long-term Time Series Predictioncited by 50
  17. 2024Fredformer: Frequency Debiased Transformer for Time Series Forecastingcited by 45
  18. 2024An Analysis of Linear Time Series Forecasting Modelscited by 41
  19. 2025Patch-wise Structural Loss for Time Series Forecastingcited by 35
  20. 2023Optimal Transport for Treatment Effect Estimationcited by 32
  21. 2024EasyTime: Time Series Forecasting Made Easycited by 30
  22. 2024Unlocking the Power of LSTM for Long Term Time Series Forecastingcited by 29
  23. 2025OLinear: A Linear Model for Time Series Forecasting in Orthogonally Transformed Domaincited by 26
  24. 2017Accelerated Alternating Projections for Robust Principal Component Analysiscited by 25
  25. 2023Irregular Traffic Time Series Forecasting Based on Asynchronous Spatio-Temporal Graph Convolutional Networkcited by 20
  26. 2023An Accurate and Interpretable Framework for Trustworthy Process Monitoringcited by 18
  27. 2025FreEformer: Frequency Enhanced Transformer for Multivariate Time Series Forecastingcited by 18
  28. 2024Fully Automated Correlated Time Series Forecasting in Minutescited by 12
  29. 2023Monotonic Neural Ordinary Differential Equation: Time-series Forecasting for Cumulative Datacited by 9
  30. 2024Proximity Matters: Local Proximity Enhanced Balancing for Treatment Effect Estimationcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 8; 2026: 14.

22 papers.

Sort:

By area:

  1. 2025DBLoss: Decomposition-based Loss Function for Time Series Forecastingcited by 45
  2. 2025Enhancing Time Series Forecasting through Selective Representation Spaces: A Patch Perspectivecited by 39
  3. 2025Aurora: Towards Universal Generative Multimodal Time Series Forecastingcited by 29
  4. 2025Bridging Past and Future: Distribution-Aware Alignment for Time Series Forecastingcited by 20
  5. 2025DistDF: Time-Series Forecasting Needs Joint-Distribution Wasserstein Alignmentcited by 13
  6. 2026GCGNet: Graph-Consistent Generative Network for Time Series Forecasting with Exogenous Variablescited by 13
  7. 2025Quadratic Direct Forecast for Training Multi-Step Time-Series Forecast Modelscited by 10
  8. 2025ASTGI: Adaptive Spatio-Temporal Graph Interactions for Irregular Multivariate Time Series Forecastingcited by 8
  9. 2026From Observations to States: Latent Time Series Forecastingcited by 6
  10. 2026Unlocking the Value of Text: Event-Driven Reasoning and Multi-Level Alignment for Time Series Forecastingcited by 5
  11. 2026PHAT: Modeling Period Heterogeneity for Multivariate Time Series Forecastingcited by 3
  12. 2026Rethinking the Role of LLMs in Time Series Forecastingcited by 3
10 more
  1. 2026Deep Time-series Forecasting Needs Kernelized Moment Balancingcited by 2
  2. 2026ST-EVO: Towards Generative Spatio-Temporal Evolution of Multi-Agent Communication Topologiescited by 1
  3. 2026Multivariate Time Series Forecasting needs Cross Variable Losscited by 1
  4. 2025Weighted Contrastive Learning for Anomaly-Aware Time-Series Forecastingcited by 0
  5. 2026Deep Time-Series Forecasting in 10 Years: A Surveycited by 0
  6. 2026LeapTS: Rethinking Time Series Forecasting as Adaptive Multi-Horizon Schedulingcited by 0
  7. 2026STaT: Resolving Shape Distortion in Non-Stationary Time Series via Tri-Modal Synergycited by 0
  8. 2026RhyMix: A Lightweight Adaptive Multi-Rhythm Network for Long-Term Time Series Forecastingcited by 0
  9. 2026CoRe: Coherence and Relational Alignment for Multivariate Time Series Forecastingcited by 0
  10. 2026XMatch: Enhancing Covariate-Aware Time Series Forecasting through Tree-Structured Exogenous Matchingcited by 0