# Adaptive Weighting Scheme for Automatic Time-Series Data Augmentation

arXiv: https://arxiv.org/abs/2102.08310 · HTML: https://mlsanity.com/paper/2102.08310/

## Key facts

- Cited by 8 papers in the map (data through 7 Oct 2026).
- Builds on 15 of its 29 references that are in the map.
- First posted on arXiv 16 Feb 2021.

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

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [InceptionTime: Finding AlexNet for Time Series Classification](https://mlsanity.com/paper/1909.04939/) (2019)
- [Deep Speech: Scaling up end-to-end speech recognition](https://mlsanity.com/paper/1412.5567/) (2014)
- [Fast AutoAugment](https://mlsanity.com/paper/1905.00397/) (2019)
- [Time Series Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2002.12478/) (2020)
- [Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations](https://mlsanity.com/paper/1805.06201/) (2018)
- [Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules](https://mlsanity.com/paper/1905.05393/) (2019)
- [Data Augmentation for Low-Resource Neural Machine Translation](https://mlsanity.com/paper/1705.00440/) (2017)
- [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)
- [Dataset Augmentation in Feature Space](https://mlsanity.com/paper/1702.05538/) (2017)
- [Learning to Compose Domain-Specific Transformations for Data Augmentation](https://mlsanity.com/paper/1709.01643/) (2017)
- [On the Generalization Effects of Linear Transformations in Data Augmentation](https://mlsanity.com/paper/2005.00695/) (2020)
- [Evaluating data augmentation for financial time series classification](https://mlsanity.com/paper/2010.15111/) (2020)

## Built on by (most cited first, 8 of 8)

- [HyperTime: Implicit Neural Representation for Time Series](https://mlsanity.com/paper/2208.05836/) (2022)
- [CADDA: Class-wise Automatic Differentiable Data Augmentation for EEG Signals](https://mlsanity.com/paper/2106.13695/) (2021)
- [Unsupervised Representation Learning for Time Series: A Review](https://mlsanity.com/paper/2308.01578/) (2023)
- [Data Augmentation for Time-Series Classification: An Extensive Empirical Study and Comprehensive Survey](https://mlsanity.com/paper/2310.10060/) (2023)
- [Fighting Money Laundering with Statistics and Machine Learning](https://mlsanity.com/paper/2201.04207/) (2022)
- [StyleTime: Style Transfer for Synthetic Time Series Generation](https://mlsanity.com/paper/2209.11306/) (2022)
- [Data Augmentation Policy Search for Long-Term Forecasting](https://mlsanity.com/paper/2405.00319/) (2024)
- [Dynamic Data Augmentation with Gating Networks for Time Series Recognition](https://mlsanity.com/paper/2111.03253/) (2021)

## Abstract (arXiv)

Data augmentation methods have been shown to be a fundamental technique to improve generalization in tasks such as image, text and audio classification. Recently, automated augmentation methods have led to further improvements on image classification and object detection leading to state-of-the-art performances. Nevertheless, little work has been done on time-series data, an area that could greatly benefit from automated data augmentation given the usually limited size of the datasets. We present two sample-adaptive automatic weighting schemes for data augmentation: the first learns to weight the contribution of the augmented samples to the loss, and the second method selects a subset of transformations based on the ranking of the predicted training loss. We validate our proposed methods on a large, noisy financial dataset and on time-series datasets from the UCR archive. On the financial dataset, we show that the methods in combination with a trading strategy lead to improvements in annualized returns of over 50%, and on the time-series data we outperform state-of-the-art models on over half of the datasets, and achieve similar performance in accuracy on the others.