arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.01568cs.LGcs.AI
收藏

多源领域自适应的信息论正则化

Information-theoretic regularization for Multi-source Domain Adaptation

KAIST(韩国科学技术院)

Geon Yeong Park, Sang Wan Lee

摘要:

对抗性学习策略在处理单源领域自适应(DA)问题方面表现出了显著的性能,近年来又被应用于多源DA(MDA)问题。虽然大多数现有的MDA策略依赖于多个域的空间表示设置,其对潜在的空间表示的影响一直知之甚少。在这里,我们采用了信息理论的方法来识别和解决潜在的不利影响的多个域鉴别器MDA:域判别信息的解体,有限的计算可扩展性,以及在训练过程中的损失梯度的大方差。我们通过将对抗性DA置于信息正则化的背景下来研究上述问题。这也为使用单一统一的域映射提供了理论依据。基于这一思想,我们实现了一种新的神经网络架构,称为多源信息正则化自适应网络(MIAN)。大规模的实验表明,MIAN,尽管其结构简单,可靠和显着优于其他国家的最先进的方法。

英文摘要:

Adversarial learning strategy has demonstrated remarkable performance in dealing with single-source Domain Adaptation (DA) problems, and it has recently been applied to Multi-source DA (MDA) problems. Although most existing MDA strategies rely on a multiple domain discriminator setting, its effect on the latent space representations has been poorly understood. Here we adopt an information-theoretic approach to identify and resolve the potential adverse effect of the multiple domain discriminators on MDA: disintegration of domain-discriminative information, limited computational scalability, and a large variance in the gradient of the loss during training. We examine the above issues by situating adversarial DA in the context of information regularization. This also provides a theoretical justification for using a single and unified domain discriminator. Based on this idea, we implement a novel neural architecture called a Multi-source Information-regularized Adaptation Networks (MIAN). Large-scale experiments demonstrate that MIAN, despite its structural simplicity, reliably and significantly outperforms other state-of-the-art methods.

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。

↑