Bias Challenges in Counterfactual Data Augmentation
This work addresses bias challenges in counterfactual data augmentation for improving OOD robustness in machine learning, but it is incremental as it identifies a specific limitation rather than proposing a new solution.
The paper tackles the problem of out-of-distribution robustness in deep learning by showing that counterfactual data augmentation, when performed by a context-guessing machine, may fail to achieve counterfactual-invariance to spurious features, as demonstrated in an exemplar NLP task.
Deep learning models tend not to be out-of-distribution robust primarily due to their reliance on spurious features to solve the task. Counterfactual data augmentations provide a general way of (approximately) achieving representations that are counterfactual-invariant to spurious features, a requirement for out-of-distribution (OOD) robustness. In this work, we show that counterfactual data augmentations may not achieve the desired counterfactual-invariance if the augmentation is performed by a context-guessing machine, an abstract machine that guesses the most-likely context of a given input. We theoretically analyze the invariance imposed by such counterfactual data augmentations and describe an exemplar NLP task where counterfactual data augmentation by a context-guessing machine does not lead to robust OOD classifiers.