arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2106.11344cs.LGcs.AIcs.CV
收藏

f域对抗学习:理论与算法

f-Domain-Adversarial Learning: Theory and Algorithms

NVIDIA(英伟达);University of Toronto(多伦多大学);Vector Institute(向量研究所);University of Waterloo(滑铁卢大学)

David Acuna, Guojun Zhang, Marc T. Law, Sanja Fidler

摘要:

无监督领域自适应用于许多机器学习应用中,其中在训练期间,模型可以访问目标域中的未标记数据以及相关的标记数据集。在本文中,我们介绍了一个新的和一般的领域对抗框架。具体而言,我们推导出一种新的泛化界领域自适应,利用一个新的措施之间的差异分布的基础上的变分特征的f-发散。它恢复了Ben-David等人的理论结果。(2010 a)作为特例,并支持实践中使用的分歧。基于这个界限,我们推导出一个新的算法框架,该框架在Ganin et al.(2016)的原始对抗训练方法中引入了一个关键修正。我们发现,在过去几年中引入的许多正则化器和ad-hoc目标并不需要达到与最先进的领域对抗方法相当(如果不是更好的话)的性能。在真实世界的自然语言和计算机视觉数据集上进行的实验分析表明,我们的框架优于现有的基线,并获得了先前在领域对抗学习中未考虑的f-分歧的最佳结果。

英文摘要:

Unsupervised domain adaptation is used in many machine learning applications where, during training, a model has access to unlabeled data in the target domain, and a related labeled dataset. In this paper, we introduce a novel and general domain-adversarial framework. Specifically, we derive a novel generalization bound for domain adaptation that exploits a new measure of discrepancy between distributions based on a variational characterization of f-divergences. It recovers the theoretical results from Ben-David et al. (2010a) as a special case and supports divergences used in practice. Based on this bound, we derive a new algorithmic framework that introduces a key correction in the original adversarial training method of Ganin et al. (2016). We show that many regularizers and ad-hoc objectives introduced over the last years in this framework are then not required to achieve performance comparable to (if not better than) state-of-the-art domain-adversarial methods. Experimental analysis conducted on real-world natural language and computer vision datasets show that our framework outperforms existing baselines, and obtains the best results for f-divergences that were not considered previously in domain-adversarial learning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑