论文标题
在组合转移下的域概括的模棱两可的变换
Equivariant Disentangled Transformation for Domain Generalization under Combination Shift
论文作者
论文摘要
当数据分布在部署环境中变化时，机器学习系统可能会遇到意外问题。一个主要原因是，在训练过程中未观察到某些域和标签的组合，而是出现在测试环境中。尽管可以应用各种基于不变性的算法，但我们发现性能增长通常是微不足道的。为了正式分析此问题，我们基于同态，均等和脱节的精致定义的概念提供了组合转移问题的独特代数表述。代数要求自然得出了一种简单而有效的方法，称为模棱两可的解开转换（EDT），该方法基于标签的代数结构来增强数据，并使转换满足均衡性和分离要求。实验结果表明，不变性可能不足，并且在组合转移问题中利用均衡结构很重要。
Machine learning systems may encounter unexpected problems when the data distribution changes in the deployment environment. A major reason is that certain combinations of domains and labels are not observed during training but appear in the test environment. Although various invariance-based algorithms can be applied, we find that the performance gain is often marginal. To formally analyze this issue, we provide a unique algebraic formulation of the combination shift problem based on the concepts of homomorphism, equivariance, and a refined definition of disentanglement. The algebraic requirements naturally derive a simple yet effective method, referred to as equivariant disentangled transformation (EDT), which augments the data based on the algebraic structures of labels and makes the transformation satisfy the equivariance and disentanglement requirements. Experimental results demonstrate that invariance may be insufficient, and it is important to exploit the equivariance structure in the combination shift problem.
