Cross-Domain Sentiment Classification via Deep Reinforcement Learning

Dou, Lintao; Huang, Jian

doi:10.1145/3578741.3578807

Cited by 1 publication

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some work utilizes the low-rank constraint to achieve domain generalization capability, such as [36][37][38]. Meta-learning has recently been applied to domain generalization, including [39][40][41]. In [42], a method integrated adversarial learning and meta-learning was proposed.…”

Section: Domain Generalizationmentioning

confidence: 99%

Adversarial and Random Transformations for Robust Domain Adaptation and Generalization

Xiao¹,

Xu²,

Zhao³

et al. 2023

Sensors

View full text Add to dashboard Cite

Data augmentation has been widely used to improve generalization in training deep neural networks. Recent works show that using worst-case transformations or adversarial augmentation strategies can significantly improve accuracy and robustness. However, due to the non-differentiable properties of image transformations, searching algorithms such as reinforcement learning or evolution strategy have to be applied, which are not computationally practical for large-scale problems. In this work, we show that by simply applying consistency training with random data augmentation, state-of-the-art results on domain adaptation (DA) and generalization (DG) can be obtained. To further improve the accuracy and robustness with adversarial examples, we propose a differentiable adversarial data augmentation method based on spatial transformer networks (STNs). The combined adversarial and random-transformation-based method outperforms the state-of-the-art on multiple DA and DG benchmark datasets. Furthermore, the proposed method shows desirable robustness to corruption, which is also validated on commonly used datasets.

show abstract