Improved OOD Generalization via Adversarial Training and Pre-training
This work addresses the challenge of model generalization for machine learning practitioners, but it is incremental as it builds on existing adversarial training and pre-training methods.
The paper tackles the problem of improving out-of-distribution (OOD) generalization by showing theoretically and empirically that adversarial training and pre-training enhance model robustness, leading to better OOD performance on image classification and natural language tasks.
Recently, learning a model that generalizes well on out-of-distribution (OOD) data has attracted great attention in the machine learning community. In this paper, after defining OOD generalization via Wasserstein distance, we theoretically show that a model robust to input perturbation generalizes well on OOD data. Inspired by previous findings that adversarial training helps improve input-robustness, we theoretically show that adversarially trained models have converged excess risk on OOD data, and empirically verify it on both image classification and natural language understanding tasks. Besides, in the paradigm of first pre-training and then fine-tuning, we theoretically show that a pre-trained model that is more robust to input perturbation provides a better initialization for generalization on downstream OOD data. Empirically, after fine-tuning, this better-initialized model from adversarial pre-training also has better OOD generalization.