# TADA: Temporal Adversarial Data Augmentation for Time Series Data

arXiv: https://arxiv.org/abs/2407.15174 · HTML: https://mlsanity.com/paper/2407.15174/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 35 references that are in the map.
- First posted on arXiv 21 Jul 2024.

## Builds on (most cited first, 20 of 20)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Domain Generalization via Invariant Feature Representation](https://mlsanity.com/paper/1301.2115/) (2013)
- [Ray: A Distributed Framework for Emerging AI Applications](https://mlsanity.com/paper/1712.05889/) (2017)
- [Measuring Robustness to Natural Distribution Shifts in Image Classification](https://mlsanity.com/paper/2007.00644/) (2020)
- [Generalizing to Unseen Domains via Adversarial Data Augmentation](https://mlsanity.com/paper/1805.12018/) (2018)
- [Learning to Learn Single Domain Generalization](https://mlsanity.com/paper/2003.13216/) (2020)
- [On Hyperparameter Optimization of Machine Learning Algorithms: Theory and Practice](https://mlsanity.com/paper/2007.15745/) (2020)
- [Learning to Diversify for Single Domain Generalization](https://mlsanity.com/paper/2108.11726/) (2021)
- [Robust and Generalizable Visual Representation Learning via Random Convolutions](https://mlsanity.com/paper/2007.13003/) (2020)
- [Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness](https://mlsanity.com/paper/2010.08001/) (2020)
- [Open Domain Generalization with Domain-Augmented Meta-Learning](https://mlsanity.com/paper/2104.03620/) (2021)
- [Respecting Domain Relations: Hypothesis Invariance for Domain Generalization](https://mlsanity.com/paper/2010.07591/) (2020)
- [WOODS: Benchmarks for Out-of-Distribution Generalization in Time Series](https://mlsanity.com/paper/2203.09978/) (2022)
- [Dynamic Time Warping as a New Evaluation for Dst Forecast with Machine Learning](https://mlsanity.com/paper/2006.04667/) (2020)
- [Optimizing Neural Network Scale for ECG Classification](https://mlsanity.com/paper/2308.12492/) (2023)

## Abstract (arXiv)

Domain generalization aim to train models to effectively perform on samples that are unseen and outside of the distribution. Adversarial data augmentation (ADA) is a widely used technique in domain generalization. It enhances the model robustness by including synthetic samples designed to simulate potential unseen scenarios into the training datasets, which is then used to train the model. However, in time series data, traditional ADA approaches often fail to address distribution shifts related to temporal characteristics. To address this limitation, we propose Temporal Adversarial Data Augmentation (TADA) for time series data, which incorporate time warping into ADA. Although time warping is inherently non-differentiable, ADA relies on generating samples through backpropagation. We resolve this issue by leveraging the duality between phase shifts in the frequency domain and time shifts in the time domain, thereby making the process differentiable. Our evaluations across various time series datasets demonstrate that TADA outperforms existing methods for domain generalization. In addition, using distribution visualization, we confirmed that the distribution shifts induced by TADA are clearly different from those induced by ADA, and together, they effectively simulate real-world distribution shifts.