@misc{cheng2020posterior,
author = {Cheng, Hao and Liu, Xiaodong and Pereira, Lis and Yu, Yaoliang and Gao, Jianfeng},
title = {Posterior Differential Regularization with f-divergence for Improving Model Robustness},
howpublished = {arXiv},
year = {2020},
month = {October},
abstract = {We address the problem of enhancing model robustness through regularization. Specifically, we focus on methods that regularize the model posterior difference between clean and noisy inputs. Theoretically, we provide a connection of two recent methods, Jacobian Regularization and Virtual Adversarial Training, under this framework. Additionally, we generalize the posterior differential regularization to the family of $f$-divergences and characterize the overall regularization framework in terms of Jacobian matrix. Empirically, we systematically compare those regularizations and standard BERT training on a diverse set of tasks to provide a comprehensive profile of their effect on model in-domain and out-of-domain generalization. For both fully supervised and semi-supervised settings, our experiments show that regularizing the posterior differential with $f$-divergence can result in well-improved model robustness. In particular, with a proper $f$-divergence, a BERT-base model can achieve comparable generalization as its BERT-large counterpart for in-domain, adversarial and domain shift scenarios, indicating the great potential of the proposed framework for boosting model generalization for NLP models.},
url = {http://approjects.co.za/?big=en-us/research/publication/posterior-differential-regularization-with-f-divergence-for-improving-model-robustness/},
}