标题： 域泛化通过不变特征表示 显示英文标题

标题： Domain Generalization via Invariant Feature Representation

摘要： 本文研究了领域泛化问题：如何从任意数量的相关领域获取知识，并将其应用于之前未见过的领域？ 我们提出了基于核函数的不变成分分析（Domain-Invariant Component Analysis, DICA）算法，该算法通过最小化领域间的差异性，同时保持输入变量与输出变量之间的功能关系，从而学习到一个不变的变换。 理论学习分析表明，减少领域间的差异性可以提高分类器在新领域上的期望泛化能力，这激发了所提出的算法。 在合成数据集和真实数据集上的实验结果表明，DICA 成功地学习到了不变特征，并在实践中提高了分类器的性能。 显示英文摘要

摘要： This paper investigates domain generalization: How to take knowledge acquired from an arbitrary number of related domains and apply it to previously unseen domains? We propose Domain-Invariant Component Analysis (DICA), a kernel-based optimization algorithm that learns an invariant transformation by minimizing the dissimilarity across domains, whilst preserving the functional relationship between input and output variables. A learning-theoretic analysis shows that reducing dissimilarity improves the expected generalization ability of classifiers on new domains, motivating the proposed algorithm. Experimental results on synthetic and real-world datasets demonstrate that DICA successfully learns invariant features and improves classifier performance in practice.