Embarrassingly Simple MixUp for Time-series
This work addresses the expensive labeling challenge in time-series data for researchers and practitioners, but it is incremental as it adapts an existing method from computer vision to a new domain.
The paper tackled the problem of limited labeled data in time-series classification by adapting the MixUp data augmentation technique to time-series, proposing MixUp++ and LatentMixUp++ for interpolation in raw and latent spaces, and extending them with semi-supervised learning. The result was significant improvements of 1% to 15% on two public datasets in both low and high labeled data regimes, with LatentMixUp++ performing best.
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++.