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.

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. We showcase data augmentation that learns a text transformation network, and data weighting that dynamically adapts the data sample importance.

Originality: The proposed framework is fairly novel and provides an interesting perspective on learning data manipulation. I found the Quality: The experiments on the text classification show that the proposed algorithms work well. However I found the experiments on image classification setting to be not very convincing (see Improvements section) Clarity: The paper is well written and organized and contains sufficient details to enable reproducing the results. Significance: The proposed algorithm is flexible to incorporate different data manipulation schemes and provides a method to learn them to improve the end-task. This might enable integrating data generation methods (GANs, VAEs) and learning an effective task-specific data-augmentation algorithms.

The paper presents a gradient based meta learning approach to automating data augmentation and weighting examples. The experiments support the advantages of the proposed technique. There are some interesting technical novelty in the proposed algorithm and a clear discussion of such novelty in the context of recent papers is beneficial. Given the similarity of the proposed technique and existing recent work on meta-learning, I recommend accepting as a poster.

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. We showcase data augmentation that learns a text transformation network, and data weighting that dynamically adapts the data sample importance.

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. We showcase data augmentation that learns a text transformation network, and data weighting that dynamically adapts the data sample importance.