2022/09/12 by S. Chandra Mouli, Mouli, S Chandra, Yangze Zhou +3
Computer Science · #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
paper · pdf · doi:10.48550/arxiv.2209.05104
openalex publication_date 2022/09/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.