# Robust Augmentation for Multivariate Time Series Classification

arXiv: https://arxiv.org/abs/2201.11739 · HTML: https://mlsanity.com/paper/2201.11739/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 25 references that are in the map.
- First posted on arXiv 27 Jan 2022.

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

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Deep learning for time series classification: a review](https://mlsanity.com/paper/1809.04356/) (2018)
- [InceptionTime: Finding AlexNet for Time Series Classification](https://mlsanity.com/paper/1909.04939/) (2019)
- [Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline](https://mlsanity.com/paper/1611.06455/) (2016)
- [ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels](https://mlsanity.com/paper/1910.13051/) (2019)
- [The UEA multivariate time series classification archive, 2018](https://mlsanity.com/paper/1811.00075/) (2018)
- [Time Series Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2002.12478/) (2020)
- [Benchmarking Multivariate Time Series Classification Algorithms](https://mlsanity.com/paper/2007.13156/) (2020)
- [LSTM Fully Convolutional Networks for Time Series Classification](https://mlsanity.com/paper/1709.05206/) (2017)
- [An Empirical Survey of Data Augmentation for Time Series Classification with Neural Networks](https://mlsanity.com/paper/2007.15951/) (2020)
- [Dataset Augmentation in Feature Space](https://mlsanity.com/paper/1702.05538/) (2017)
- [Attend and Diagnose: Clinical Time Series Analysis using Attention Models](https://mlsanity.com/paper/1711.03905/) (2017)
- [Self-attention for raw optical Satellite Time Series Classification](https://mlsanity.com/paper/1910.10536/) (2019)
- [The Canonical Interval Forest (CIF) Classifier for Time Series Classification](https://mlsanity.com/paper/2008.09172/) (2020)
- [Improving the Accuracy of Global Forecasting Models using Time Series Data Augmentation](https://mlsanity.com/paper/2008.02663/) (2020)
- [Quantifying the vanishing gradient and long distance dependency problem in recursive neural networks and recursive LSTMs](https://mlsanity.com/paper/1603.00423/) (2016)
- [Predictive Maintenance for General Aviation Using Convolutional Transformers](https://mlsanity.com/paper/2110.03757/) (2021)

## Built on by (most cited first, 4 of 4)

- [Empirical Study of Mix-based Data Augmentation Methods in Physiological Time Series Data](https://mlsanity.com/paper/2309.09970/) (2023)
- [Time Series Viewmakers for Robust Disruption Prediction](https://mlsanity.com/paper/2410.11065/) (2024)
- [An Empirical Evaluation of Multivariate Time Series Classification with Input Transformation across Different Dimensions](https://mlsanity.com/paper/2210.07713/) (2022)
- [Compositionality in Time Series: A Proof of Concept using Symbolic Dynamics and Compositional Data Augmentation](https://mlsanity.com/paper/2508.20656/) (2025)

## Abstract (arXiv)

Neural networks are capable of learning powerful representations of data, but they are susceptible to overfitting due to the number of parameters. This is particularly challenging in the domain of time series classification, where datasets may contain fewer than 100 training examples. In this paper, we show that the simple methods of cutout, cutmix, mixup, and window warp improve the robustness and overall performance in a statistically significant way for convolutional, recurrent, and self-attention based architectures for time series classification. We evaluate these methods on 26 datasets from the University of East Anglia Multivariate Time Series Classification (UEA MTSC) archive and analyze how these methods perform on different types of time series data.. We show that the InceptionTime network with augmentation improves accuracy by 1% to 45% in 18 different datasets compared to without augmentation. We also show that augmentation improves accuracy for recurrent and self attention based architectures.