Robustness through Data Augmentation Loss Consistency

Published: 25 Jan 2023, Last Modified: 30 Jun 2023Accepted by TMLREveryoneRevisionsBibTeX
Authors that are also TMLR Expert Reviewers: ~Ahmad_Beirami1
Abstract: While deep learning through empirical risk minimization (ERM) has succeeded at achieving human-level performance at a variety of complex tasks, ERM is not robust to distribution shifts or adversarial attacks. Synthetic data augmentation followed by empirical risk minimization (DA-ERM) is a simple and widely used solution to improve robustness in ERM. In addition, consistency regularization can be applied to further improve the robustness of the model by forcing the representation of the original sample and the augmented one to be similar. However, existing consistency regularization methods are not applicable to covariant data augmentation, where the label in the augmented sample is dependent on the augmentation function. For example, dialog state covaries with named entity when we augment data with a new named entity. In this paper, we propose data augmented loss invariant regularization (DAIR), a simple form of consistency regularization that is applied directly at the loss level rather than intermediate features, making it widely applicable to both invariant and covariant data augmentation regardless of network architecture, problem setup, and task. We apply DAIR to real-world learning problems involving covariant data augmentation: robust neural task-oriented dialog state tracking and robust visual question answering. We also apply DAIR to tasks involving invariant data augmentation: robust regression, robust classification against adversarial attacks, and robust ImageNet classification under distribution shift. Our experiments show that DAIR consistently outperforms ERM and DA-ERM with little marginal computational cost and sets new state-of-the-art results in several benchmarks involving covariant data augmentation. Our code of all experiments are available at:
Certifications: Expert Certification
Submission Length: Regular submission (no more than 12 pages of main content)
Changes Since Last Submission: Moved acknowledgement to the first page.
Assigned Action Editor: ~Kui_Jia1
License: Creative Commons Attribution 4.0 International (CC BY 4.0)
Submission Number: 309