A crucial aspect in reliable machine learning is to design a deployable system in generalizing new related but unobserved environments. Domain generalization aims to alleviate such a prediction gap between the observed and unseen environments. Previous approaches commonly incorporated learning invariant representation for achieving good empirical performance. In this paper, we reveal that merely learning invariant representation is vulnerable to the unseen environment. To this end, we derive novel theoretical analysis to control the unseen test environment error in the representation learning, which highlights the importance of controlling the smoothness of representation. In practice, our analysis further inspires an efficient regularization method to improve the robustness in domain generalization. Our regularization is orthogonal to and can be straightforwardly adopted in existing domain generalization algorithms for invariant representation learning. Empirical results show that our algorithm outperforms the base versions in various dataset and invariance criteria.
翻译:可靠的机器学习的一个关键方面是设计一个可部署的系统,将新的相关但不可观测的环境推广为通用环境; 域的概括化旨在缩小观测到的环境和不可见的环境之间的预测差距; 以往的方法通常包含学习的变异性代表,以取得良好的实证表现; 在本文中,我们发现,仅仅学习无差异的表示方式很容易受到不可见的环境的影响。 为此,我们从理论上进行新颖的分析,以控制代表性学习中的隐性测试环境错误,这突出表明控制代表性的顺利性的重要性。 实际上,我们的分析进一步激励一种有效的正规化方法,以提高域的稳健性。 我们的正规化与现有的域通用算法是交替的,并且可以直接用于现有的域通用算法,以便进行不固定式代表学习。 经验性结果显示,我们的算法超越了各种数据集和变量标准的基础版本。