mlsanityData to 14 Oct 2026

Improving Time Series Forecasting via Instance-aware Post-hoc Revision

arXiv 2505.23583 ↗First posted 29 May 2025cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

Time series forecasting plays a vital role in various real-world applications and has attracted significant attention in recent decades. While recent methods have achieved remarkable accuracy by incorporating advanced inductive biases and training strategies, we observe that instance-level variations remain a significant challenge. These variations--stemming from distribution shifts, missing data, and long-tail patterns--often lead to suboptimal forecasts for specific instances, even when overall performance appears strong. To address this issue, we propose a model-agnostic framework, PIR, designed to enhance forecasting performance through Post-forecasting Identification and Revision. Specifically, PIR first identifies biased forecasting instances by estimating their accuracy. Based on this, the framework revises the forecasts using contextual information, including covariates and historical time series, from both local and global perspectives in a post-processing fashion. Extensive experiments on real-world datasets with mainstream forecasting models demonstrate that PIR effectively mitigates instance-level errors and significantly improves forecasting reliability.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 31 of its 54 references that are in the map. First posted on arXiv 29 May 2025.

Builds on

31 of 54 references.

References · 31

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  4. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  5. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  6. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,210
  7. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,013
  8. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 879
  9. 2019Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecastingcited by 761
  10. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 753
  11. 2024Unified Training of Universal Time Series Forecasting Transformerscited by 614
  12. 2019Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecastingcited by 607
19 more
  1. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 582
  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. 2024TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methodscited by 249
  5. 2024TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variablescited by 248
  6. 2017A Multi-Horizon Quantile Recurrent Forecastercited by 211
  7. 2024Deep Time Series Models: A Comprehensive Survey and Benchmarkcited by 197
  8. 2020A review on outlier/anomaly detection in time series datacited by 189
  9. 2023Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Surveycited by 140
  10. 2024SparseTSF: Modeling Long-term Time Series Forecasting with 1k Parameterscited by 107
  11. 2023Dish-TS: A General Paradigm for Alleviating Distribution Shift in Time Series Forecastingcited by 93
  12. 2024Context is Key: A Benchmark for Forecasting with Essential Textual Informationcited by 87
  13. 2021Neural basis expansion analysis with exogenous variables: Forecasting electricity prices with NBEATSxcited by 64
  14. 2024Retrieval Augmented Time Series Forecastingcited by 46
  15. 2023TimeMAE: Self-Supervised Representations of Time Series with Decoupled Masked Autoencoderscited by 44
  16. 2024Revitalizing Multivariate Time Series Forecasting: Learnable Decomposition with Inter-Series Dependencies and Intra-Series Variations Modelingcited by 44
  17. 2024Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicatorscited by 32
  18. 2024Time-Series Forecasting for Out-of-Distribution Generalization Using Invariant Learningcited by 27
  19. 2024Rethinking the Power of Timestamps for Robust Time Series Forecasting: A Global-Local Fusion Perspectivecited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 13.

15 papers.

Sort:

By area:

  1. 2026AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discoverycited by 23
  2. 2025AlphaCast: A Human Wisdom-LLM Intelligence Co-Reasoning Framework for Interactive Time Series Forecastingcited by 12
  3. 2026Position: Beyond Model-Centric Prediction -- Agentic Time Series Forecastingcited by 9
  4. 2026Stationarity-Aware Retrieval-Augmented Time Series Forecastingcited by 5
  5. 2026CastFlow: Learning Role-Specialized Agentic Workflows for Time Series Forecastingcited by 2
  6. 2025Causality-Inspired Safe Residual Correction for Multivariate Time Seriescited by 1
  7. 2026StaTS: Spectral Trajectory Schedule Learning for Adaptive Time Series Forecasting with Frequency Guided Denoisercited by 1
  8. 2026Dual-Prototype Disentanglement: A Context-Aware Enhancement Framework for Time Series Forecastingcited by 0
  9. 2026Hedging Memory Horizons for Non-Stationary Prediction via Online Aggregationcited by 0
  10. 2026Online Irregular Multivariate Time Series Forecasting via Uncertainty-Driven Dual-Expert Calibrationcited by 0
  11. 2026UniWind: Day-Ahead Wind Power Forecasting via Physics-Informed State Routingcited by 0
  12. 2026Which Histories Matter for Time Series Forecasting? Learning Predictive Relevance with Future Supervisioncited by 0
3 more
  1. 2026Downside-Controlled Online Forecast Combination under Delayed and Revised Outcomescited by 0
  2. 2026JudgeCast: Time Series Forecasting with Experience-Informed Covariate Judgementscited by 0
  3. 2026TIMBRE: Teaching Time Series Forecasters to Read, Remember, and Reconcilecited by 0