# Self-Adaptive Forecasting for Improved Deep Learning on Non-Stationary Time-Series

arXiv: https://arxiv.org/abs/2202.02403 · HTML: https://mlsanity.com/paper/2202.02403/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 45 references that are in the map.
- First posted on arXiv 4 Feb 2022.

## Builds on (most cited first, 22 of 22)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks](https://mlsanity.com/paper/1704.04110/) (2017)
- [Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting](https://mlsanity.com/paper/1912.09363/) (2019)
- [N-BEATS: Neural basis expansion analysis for interpretable time series forecasting](https://mlsanity.com/paper/1905.10437/) (2019)
- [Improving robustness against common corruptions by covariate shift adaptation](https://mlsanity.com/paper/2006.16971/) (2020)
- [Contrastive Adaptation Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1901.00976/) (2019)
- [A Multi-Horizon Quantile Recurrent Forecaster](https://mlsanity.com/paper/1711.11053/) (2017)
- [Self-Supervised Policy Adaptation during Deployment](https://mlsanity.com/paper/2007.04309/) (2020)
- [Rethinking Importance Weighting for Deep Learning under Distribution Shift](https://mlsanity.com/paper/2006.04662/) (2020)
- [Principles and Algorithms for Forecasting Groups of Time Series: Locality and Globality](https://mlsanity.com/paper/2008.00444/) (2020)
- [MT3: Meta Test-Time Training for Self-Supervised Test-Time Adaption](https://mlsanity.com/paper/2103.16201/) (2021)
- [Test-Time Training with Self-Supervision for Generalization under Distribution Shifts](https://mlsanity.com/paper/1909.13231/) (2019)
- [Robust Out-of-distribution Detection for Neural Networks](https://mlsanity.com/paper/2003.09711/) (2020)
- [Mandoline: Model Evaluation under Distribution Shift](https://mlsanity.com/paper/2107.00643/) (2021)
- [SPICE: Self-supervised Pitch Estimation](https://mlsanity.com/paper/1910.11664/) (2019)
- [Hedging Cryptocurrency Options](https://mlsanity.com/paper/2112.06807/) (2021)

## Built on by (most cited first, 14 of 14)

- [Beyond Model Adaptation at Test Time: A Survey](https://mlsanity.com/paper/2411.03687/) (2024)
- [Koopman Neural Forecaster for Time Series with Temporal Distribution Shifts](https://mlsanity.com/paper/2210.03675/) (2022)
- [RobustTSF: Towards Theory and Design of Robust Time Series Forecasting with Anomalies](https://mlsanity.com/paper/2402.02032/) (2024)
- [Online Test-Time Adaptation of Spatial-Temporal Traffic Flow Forecasting](https://mlsanity.com/paper/2401.04148/) (2024)
- [Selective Learning for Deep Time Series Forecasting](https://mlsanity.com/paper/2510.25207/) (2025)
- [Test Time Learning for Time Series Forecasting](https://mlsanity.com/paper/2409.14012/) (2024)
- [Adaptive Sampling for Probabilistic Forecasting under Distribution Shift](https://mlsanity.com/paper/2302.11870/) (2023)
- [DAM: A Universal Dual Attention Mechanism for Multimodal Timeseries Cryptocurrency Trend Forecasting](https://mlsanity.com/paper/2405.00522/) (2024)
- [Population Age Group Sensitivity for COVID-19 Infections with Deep Learning](https://mlsanity.com/paper/2307.00751/) (2023)
- [AdaNODEs: Test Time Adaptation for Time Series Forecasting Using Neural ODEs](https://mlsanity.com/paper/2601.12893/) (2026)
- [Interpreting County Level COVID-19 Infection and Feature Sensitivity using Deep Learning Time Series Models](https://mlsanity.com/paper/2210.03258/) (2022)
- [Prompting-based Temporal Domain Generalization](https://mlsanity.com/paper/2310.02473/) (2023)
- [Incorporating Long-term Data in Training Short-term Traffic Prediction Model](https://mlsanity.com/paper/2410.14726/) (2024)
- [Contrastive Time Series Forecasting with Anomalies](https://mlsanity.com/paper/2512.11526/) (2025)

## Abstract (arXiv)

Real-world time-series datasets often violate the assumptions of standard supervised learning for forecasting -- their distributions evolve over time, rendering the conventional training and model selection procedures suboptimal. In this paper, we propose a novel method, Self-Adaptive Forecasting (SAF), to modify the training of time-series forecasting models to improve their performance on forecasting tasks with such non-stationary time-series data. SAF integrates a self-adaptation stage prior to forecasting based on `backcasting', i.e. predicting masked inputs backward in time. This is a form of test-time training that creates a self-supervised learning problem on test samples before performing the prediction task. In this way, our method enables efficient adaptation of encoded representations to evolving distributions, leading to superior generalization. SAF can be integrated with any canonical encoder-decoder based time-series architecture such as recurrent neural networks or attention-based architectures. On synthetic and real-world datasets in domains where time-series data are known to be notoriously non-stationary, such as healthcare and finance, we demonstrate a significant benefit of SAF in improving forecasting accuracy.