Wave-Mask/Mix: Exploring Wavelet-Based Augmentations for Time Series Forecasting

TL;DR

This paper introduces WaveMask and WaveMix, two wavelet-based data augmentation methods for multivariate time series forecasting that preserve temporal dependencies and improve model performance, especially with limited data.

Contribution

It is the first extensive study applying discrete wavelet transform for augmentation in multivariate time series forecasting, demonstrating competitive results.

Findings

WaveMask and WaveMix outperform baseline methods in forecasting accuracy.

The methods are effective in cold-start scenarios with limited data.

Wavelet-based augmentation maintains temporal coherence in time series data.

Abstract

Data augmentation is important for improving machine learning model performance when faced with limited real-world data. In time series forecasting (TSF), where accurate predictions are crucial in fields like finance, healthcare, and manufacturing, traditional augmentation methods for classification tasks are insufficient to maintain temporal coherence. This research introduces two augmentation approaches using the discrete wavelet transform (DWT) to adjust frequency elements while preserving temporal dependencies in time series data. Our methods, Wavelet Masking (WaveMask) and Wavelet Mixing (WaveMix), are evaluated against established baselines across various forecasting horizons. To the best of our knowledge, this is the first study to conduct extensive experiments on multivariate time series using Discrete Wavelet Transform as an augmentation technique. Experimental results demonstrate that our techniques achieve competitive results with previous methods. We also explore cold-start forecasting using downsampled training datasets, comparing outcomes to baseline methods.