arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.12815cs.LGstat.ML
收藏

基于公共特定低秩分解的高效领域泛化

Efficient Domain Generalization via Common-Specific Low-Rank Decomposition

MSR India(微软研究院印度);IIT Bombay(印度理工学院孟买分校)

Vihari Piratla, Praneeth Netrapalli, Sunita Sarawagi

摘要:

领域泛化是指训练模型的任务,该模型泛化到在训练期间未看到的新领域。我们提出了CSD(公共特定分解),对于这种设置,它联合学习一个公共组件(推广到新的领域)和一个特定于领域的组件(过度拟合训练域)。在训练之后丢弃域特定分量,并且仅保留公共分量。该算法是非常简单的,只涉及修改任何给定的神经网络架构的最终线性分类层。我们提出了一个原则性的分析,了解现有的方法,提供可识别的结果CSD,并研究低秩的领域泛化的影响。我们表明,CSD匹配或击败最先进的方法,领域泛化的基础上域擦除,域扰动数据增强,和元学习。进一步诊断旋转MNIST,域是可解释的,证实了这一假设,CSD成功地解开共同和域特定的组件,从而导致更好的领域泛化。

英文摘要:

Domain generalization refers to the task of training a model which generalizes to new domains that are not seen during training. We present CSD (Common Specific Decomposition), for this setting,which jointly learns a common component (which generalizes to new domains) and a domain specific component (which overfits on training domains). The domain specific components are discarded after training and only the common component is retained. The algorithm is extremely simple and involves only modifying the final linear classification layer of any given neural network architecture. We present a principled analysis to understand existing approaches, provide identifiability results of CSD,and study effect of low-rank on domain generalization. We show that CSD either matches or beats state of the art approaches for domain generalization based on domain erasure, domain perturbed data augmentation, and meta-learning. Further diagnostics on rotated MNIST, where domains are interpretable, confirm the hypothesis that CSD successfully disentangles common and domain specific components and hence leads to better domain generalization.

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。

↑