DaMSTF: Domain Adversarial Learning Enhanced Meta Self-Training for Domain Adaptation
Self-training emerges as an important research line on domain adaptation. By taking the model's prediction as the pseudo labels of the unlabeled data, self-training bootstraps the model with pseudo instances in the target domain. However, the prediction errors of pseudo labels (label noise) challenge the performance of self-training. To address this problem, previous approaches only use reliable pseudo instances, i.e., pseudo instances with high prediction confidence, to retrain the model. Although these strategies effectively reduce the label noise, they are prone to miss the hard examples. In this paper, we propose a new self-training framework for domain adaptation, namely Domain adversarial learning enhanced Self-Training Framework (DaMSTF). Firstly, DaMSTF involves meta-learning to estimate the importance of each pseudo instance, so as to simultaneously reduce the label noise and preserve hard examples. Secondly, we design a meta constructor for constructing the meta-validation set, which guarantees the effectiveness of the meta-learning module by improving the quality of the meta-validation set. Thirdly, we find that the meta-learning module suffers from the training guidance vanishment and tends to converge to an inferior optimal. To this end, we employ domain adversarial learning as a heuristic neural network initialization method, which can help the meta-learning module converge to a better optimal. Theoretically and experimentally, we demonstrate the effectiveness of the proposed DaMSTF. On the cross-domain sentiment classification task, DaMSTF improves the performance of BERT with an average of nearly 4%.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationMeta-LearningSentiment AnalysisSentiment ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
SRoUDA: Meta Self-training for Robust Unsupervised Domain Adaptation
As acquiring manual labels on data could be costly, unsupervised domain adaptation (UDA), which transfers knowledge learned from a rich-label dataset to the unlabeled target dataset, is gaining increasing popularity. Whi…
Adversarial RobustnessDomain AdaptationUnsupervised Domain AdaptationDebiased Dual-Invariant Defense for Adversarially Robust Person Re-Identification
Person re-identification (ReID) is a fundamental task in many real-world applications such as pedestrian trajectory tracking. However, advanced deep learning-based ReID models are highly susceptible to adversarial attack…
Person Re-IdentificationAdversarial DefenseMetric LearningMetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptation
For unsupervised domain adaptation (UDA), to alleviate the effect of domain shift, many approaches align the source and target domains in the feature space by adversarial learning or by explicitly aligning their statisti…
ClassificationDomain AdaptationGeneral ClassificationMeta-Learning+4Hierarchical Self-Supervised Adversarial Training for Robust Vision Models in Histopathology
Adversarial attacks pose significant challenges for vision models in critical fields like healthcare, where reliability is essential. Although adversarial training has been well studied in natural images, its application…
Contrastive LearningLearning Transferable Adversarial Robust Representations via Multi-view Consistency
Despite the success on few-shot learning problems, most meta-learned models only focus on achieving good performance on clean examples and thus easily break down when given adversarially perturbed samples. While some rec…
Adversarial AttackAdversarial RobustnessDomain AdaptationFew-Shot Learning+3