DropoutTS: Sample-Adaptive Dropout for Robust Time Series Forecasting
Not on the map. Why?
Abstract (arXiv)
Deep time series models are vulnerable to noisy data ubiquitous in real-world applications. Existing robustness strategies either prune data or rely on costly prior quantification, failing to balance effectiveness and efficiency. In this paper, we introduce DropoutTS, a model-agnostic plugin that shifts the paradigm from "what" to learn to "how much" to learn. DropoutTS employs a Sample-Adaptive Dropout mechanism: leveraging spectral sparsity to efficiently quantify instance-level noise via reconstruction residuals, it dynamically calibrates model learning capacity by mapping noise to adaptive dropout rates - selectively suppressing spurious fluctuations while preserving fine-grained fidelity. Extensive experiments across diverse noise regimes and open benchmarks show DropoutTS consistently boosts superior backbones' performance, delivering advanced robustness with negligible parameter overhead and no architectural modifications. Our code is available at https://github.com/CityMind-Lab/DropoutTS.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 24 of its 41 references that are in the map. First posted on arXiv 29 Jan 2026.
Builds on
24 of 41 references.
References · 24
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
- 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 1,981
- 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
- 2022Are Transformers Effective for Time Series Forecasting?cited by 1,400
- 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,200
- 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,030
- 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 906
- 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 869
- 2020Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networkscited by 563
- 2015Variational Dropout and the Local Reparameterization Trickcited by 489
- 2020Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Userscited by 336
- 2021Spectral Temporal Graph Neural Network for Multivariate Time-series Forecastingcited by 298
12 more
- 2017Concrete Dropoutcited by 227
- 2022Diffusion-based Time Series Imputation and Forecasting with Structured State Space Modelscited by 195
- 2023Frequency-domain MLPs are More Effective Learners in Time Series Forecastingcited by 170
- 2013Dropout Training as Adaptive Regularizationcited by 89
- 2018Deep Learning with Long Short-Term Memory for Time Series Predictioncited by 39
- 2025Temporal Query Network for Efficient Multivariate Time Series Forecastingcited by 29
- 2019Recurrent Neural Networks for Time Series Forecastingcited by 19
- 2024Are Self-Attentions Effective for Time Series Forecasting?cited by 18
- 2024RobustTSF: Towards Theory and Design of Robust Time Series Forecasting with Anomaliescited by 17
- 2025Selective Learning for Deep Time Series Forecastingcited by 8
- 2025Not All Data are Good Labels: On the Self-supervised Labeling for Time Series Forecastingcited by 4
- 2025SynEVO: A neuro-inspired spatiotemporal evolutional framework for cross-domain adaptationcited by 1
Built on by
Citing papers per year: 2026: 3.
3 papers.