Timezone: »

Learning to Compose Domain-Specific Transformations for Data Augmentation
Alexander Ratner · Henry Ehrenberg · Zeshan Hussain · Jared Dunnmon · Christopher Ré

Wed Dec 06 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #119

Data augmentation is a ubiquitous technique for increasing the size of labeled training sets by leveraging task-specific data transformations that preserve class labels. While it is often easy for domain experts to specify individual transformations, constructing and tuning the more sophisticated compositions typically needed to achieve state-of-the-art results is a time-consuming manual task in practice. We propose a method for automating this process by learning a generative sequence model over user-specified transformation functions using a generative adversarial approach. Our method can make use of arbitrary, non-deterministic transformation functions, is robust to misspecified user input, and is trained on unlabeled data. The learned transformation model can then be used to perform data augmentation for any end discriminative model. In our experiments, we show the efficacy of our approach on both image and text datasets, achieving improvements of 4.0 accuracy points on CIFAR-10, 1.4 F1 points on the ACE relation extraction task, and 3.4 accuracy points when using domain-specific transformation operations on a medical imaging dataset as compared to standard heuristic augmentation approaches.

Author Information

Alexander Ratner (Stanford)
Henry Ehrenberg (Stanford University)
Zeshan Hussain (Stanford University)
Jared Dunnmon (Stanford University)

-- Postdoctoral scholar with Prof. Chris Re at Stanford University -- Foci include multi-modal weak supervision and data augmentation

Christopher Ré (Stanford)

More from the Same Authors