Dynamic Data Augmentation with Gating Networks for Time Series Recognition
This addresses the challenge of optimizing data augmentation for time series data, which is incremental as it builds on existing augmentation techniques with a novel selection mechanism.
The paper tackles the problem of selecting effective data augmentation methods for time series recognition by proposing a neural network that dynamically chooses combinations using a gating network and feature consistency loss, achieving demonstrated effectiveness on 12 large time-series datasets from the UCR archive.
Data augmentation is a technique to improve the generalization ability of machine learning methods by increasing the size of the dataset. However, since every augmentation method is not equally effective for every dataset, you need to select an appropriate method carefully. We propose a neural network that dynamically selects the best combination of data augmentation methods using a mutually beneficial gating network and a feature consistency loss. The gating network is able to control how much of each data augmentation is used for the representation within the network. The feature consistency loss gives a constraint that augmented features from the same input should be in similar. In experiments, we demonstrate the effectiveness of the proposed method on the 12 largest time-series datasets from 2018 UCR Time Series Archive and reveal the relationships between the data augmentation methods through analysis of the proposed method.