Data Augmentation Policy Search for Long-Term Forecasting

TL;DR

This paper introduces TSAA, an automatic data augmentation method for long-term time-series forecasting that improves model performance by optimizing augmentation policies through a bilevel process.

Contribution

The paper presents TSAA, a novel efficient and easy-to-implement automatic augmentation approach specifically designed for long-term time-series forecasting tasks.

Findings

TSAA outperforms several baseline methods on benchmark datasets.

The approach effectively identifies robust augmentation policies.

It enhances long-term forecasting accuracy across univariate and multivariate problems.

Abstract

Data augmentation serves as a popular regularization technique to combat overfitting challenges in neural networks. While automatic augmentation has demonstrated success in image classification tasks, its application to time-series problems, particularly in long-term forecasting, has received comparatively less attention. To address this gap, we introduce a time-series automatic augmentation approach named TSAA, which is both efficient and easy to implement. The solution involves tackling the associated bilevel optimization problem through a two-step process: initially training a non-augmented model for a limited number of epochs, followed by an iterative split procedure. During this iterative process, we alternate between identifying a robust augmentation policy through Bayesian optimization and refining the model while discarding suboptimal runs. Extensive evaluations on challenging univariate and multivariate forecasting benchmark problems demonstrate that TSAA consistently outperforms several robust baselines, suggesting its potential integration into prediction pipelines. Code is available at this repository: https://github.com/azencot-group/TSAA.