Embarrassingly Simple MixUp for Time-series

TL;DR

This paper adapts and extends the MixUp data augmentation technique for time series classification, introducing MixUp++ and LatentMixUp++ with semi-supervised learning, leading to significant accuracy improvements across datasets.

Contribution

The paper proposes simple modifications to MixUp for raw time series and latent space interpolation, enhancing data augmentation in limited labeled data scenarios.

Findings

Significant accuracy improvements of 1-15% on two datasets.

Effective use of semi-supervised learning with the proposed methods.

Applicable to both low and high labeled data regimes.

Abstract

Labeling time series data is an expensive task because of domain expertise and dynamic nature of the data. Hence, we often have to deal with limited labeled data settings. Data augmentation techniques have been successfully deployed in domains like computer vision to exploit the use of existing labeled data. We adapt one of the most commonly used technique called MixUp, in the time series domain. Our proposed, MixUp++ and LatentMixUp++, use simple modifications to perform interpolation in raw time series and classification model's latent space, respectively. We also extend these methods with semi-supervised learning to exploit unlabeled data. We observe significant improvements of 1\% - 15\% on time series classification on two public datasets, for both low labeled data as well as high labeled data regimes, with LatentMixUp++.