Learning Data Manipulation for Augmentation and Weighting
This work addresses data manipulation for model training, offering a flexible method that can be applied to various schemes, but it is incremental as it builds on existing reinforcement learning connections.
The paper tackles the problem of improving model training by learning data manipulation schemes, such as augmentation and weighting, using a unified gradient-based algorithm, and shows that it significantly enhances image and text classification performance in low-data and class-imbalance scenarios.
Manipulating data, such as weighting data examples or augmenting with new instances, has been increasingly used to improve model training. Previous work has studied various rule- or learning-based approaches designed for specific types of data manipulation. In this work, we propose a new method that supports learning different manipulation schemes with the same gradient-based algorithm. Our approach builds upon a recent connection of supervised learning and reinforcement learning (RL), and adapts an off-the-shelf reward learning algorithm from RL for joint data manipulation learning and model training. Different parameterization of the "data reward" function instantiates different manipulation schemes. We showcase data augmentation that learns a text transformation network, and data weighting that dynamically adapts the data sample importance. Experiments show the resulting algorithms significantly improve the image and text classification performance in low data regime and class-imbalance problems.