# Towards Diverse and Coherent Augmentation for Time-Series Forecasting

arXiv: https://arxiv.org/abs/2303.14254 · HTML: https://mlsanity.com/paper/2303.14254/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 29 references that are in the map.
- First posted on arXiv 24 Mar 2023.

## Builds on (most cited first, 15 of 15)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs](https://mlsanity.com/paper/1706.02633/) (2017)
- [Time Series Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2002.12478/) (2020)
- [Data Augmentation of Wearable Sensor Data for Parkinson's Disease Monitoring using Convolutional Neural Networks](https://mlsanity.com/paper/1706.00527/) (2017)
- [An Empirical Survey of Data Augmentation for Time Series Classification with Neural Networks](https://mlsanity.com/paper/2007.15951/) (2020)
- [RobustTAD: Robust Time Series Anomaly Detection via Decomposition and Convolutional Neural Networks](https://mlsanity.com/paper/2002.09545/) (2020)
- [GRATIS: GeneRAting TIme Series with diverse and controllable characteristics](https://mlsanity.com/paper/1903.02787/) (2019)
- [Data augmentation using synthetic data for time series classification with deep residual networks](https://mlsanity.com/paper/1808.02455/) (2018)
- [Boosting Deep Learning Risk Prediction with Generative Adversarial Networks for Electronic Health Records](https://mlsanity.com/paper/1709.01648/) (2017)
- [DOPING: Generative Data Augmentation for Unsupervised Anomaly Detection with GAN](https://mlsanity.com/paper/1808.07632/) (2018)
- [Improving the Accuracy of Global Forecasting Models using Time Series Data Augmentation](https://mlsanity.com/paper/2008.02663/) (2020)
- [T-CGAN: Conditional Generative Adversarial Network for Data Augmentation in Noisy Time Series with Irregular Sampling](https://mlsanity.com/paper/1811.08295/) (2018)

## Built on by (most cited first, 7 of 7)

- [Towards a General Time Series Forecasting Model with Unified Representation and Adaptive Transfer](https://mlsanity.com/paper/2405.17478/) (2024)
- [Finding Order in Chaos: A Novel Data Augmentation Method for Time Series in Contrastive Learning](https://mlsanity.com/paper/2309.13439/) (2023)
- [Segment, Shuffle, and Stitch: A Simple Layer for Improving Time-Series Representations](https://mlsanity.com/paper/2405.20082/) (2024)
- [Wave-Mask/Mix: Exploring Wavelet-Based Augmentations for Time Series Forecasting](https://mlsanity.com/paper/2408.10951/) (2024)
- [Dominant Shuffle: A Simple Yet Powerful Data Augmentation for Time-series Prediction](https://mlsanity.com/paper/2405.16456/) (2024)
- [EMGFlow: Robust and Efficient Surface Electromyography Synthesis via Flow Matching](https://mlsanity.com/paper/2604.13685/) (2026)
- [SASG-DA: Sparse-Aware Semantic-Guided Diffusion Augmentation For Myoelectric Gesture Recognition](https://mlsanity.com/paper/2511.08344/) (2025)

## Abstract (arXiv)

Time-series data augmentation mitigates the issue of insufficient training data for deep learning models. Yet, existing augmentation methods are mainly designed for classification, where class labels can be preserved even if augmentation alters the temporal dynamics. We note that augmentation designed for forecasting requires diversity as well as coherence with the original temporal dynamics. As time-series data generated by real-life physical processes exhibit characteristics in both the time and frequency domains, we propose to combine Spectral and Time Augmentation (STAug) for generating more diverse and coherent samples. Specifically, in the frequency domain, we use the Empirical Mode Decomposition to decompose a time series and reassemble the subcomponents with random weights. This way, we generate diverse samples while being coherent with the original temporal relationships as they contain the same set of base components. In the time domain, we adapt a mix-up strategy that generates diverse as well as linearly in-between coherent samples. Experiments on five real-world time-series datasets demonstrate that STAug outperforms the base models without data augmentation as well as state-of-the-art augmentation methods.