Timezone: »

 
Poster
Learning Data Manipulation for Augmentation and Weighting
Zhiting Hu · Bowen Tan · Russ Salakhutdinov · Tom Mitchell · Eric Xing

Thu Dec 12 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #162
in Deep Learning -- Efficient Training Methods »

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.

Keywords: Deep Learning -> Efficient Training Methods · Algorithms -> Classification; Deep Learning -> Supervised Deep Networks

Author Information

Zhiting Hu (Carnegie Mellon University)
Bowen Tan (CMU)
Russ Salakhutdinov (Carnegie Mellon University)
Tom Mitchell (Carnegie Mellon University)
Eric Xing (Petuum Inc. / Carnegie Mellon University)

More from the Same Authors