发表机构
School of Mathematical Sciences, University of Chinese Academy of Sciences; Key Laboratory of Big Data Mining and Knowledge Management, Chinese Academy of Sciences（中国科学院大学数学科学学院; 中国科学院大数据挖掘与知识管理重点实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对领域泛化中域调节因果-响应映射的问题，提出LADDER方法，通过固定模型的源域分类器重加权实现目标域泛化，在模拟、FMoW等数据集上提升了整体与组平均准确率。
AI 中文摘要
领域泛化（DG）旨在从多个源域学习并泛化到未见过的目标域。大多数DG方法追求不变性：它们寻找跨域预测规则不变的因果表示。该原则在因果机制稳定时有效，但当域本身调节因果内容到响应的映射时，就会变得受限。在这种情况下，直接将域风格输入预测器会产生误导性捷径，因为风格本身并不导致响应。然而，多种风格的明显混乱可以成为一个阶梯：风格可以在源域中定位未见过的目标域，并指导应信任哪些依赖域的预测规则。我们提出Latent Adaptive Domain Disentanglement and Environment Reweighting（LADDER，隐式自适应领域解缠与环境重加权），这是一种固定模型的DG流程，学习因果/风格表示，冻结编码器，拟合源特定分类器，仅在推理时使用未标记的目标域协变量集来计算这些固定分类器的权重，无需目标标签或模型状态更新。我们为源重加权建立理论保证，并在模拟、FMoW和按位置分组的iWildCam协议上验证LADDER，在整体和组平均准确率上均有提升。
英文摘要
Domain generalization (DG) aims to learn from multiple source domains and generalize to unseen target domains. Most DG methods pursue invariance: they seek a causal representation whose prediction rule is invariant across domains. This principle is effective when the causal mechanism is stable, but becomes restrictive when the domain itself modulates how causal content maps to the response. In this case, directly feeding domain style into the predictor can create misleading shortcuts, since style does not by itself cause the response. Yet the apparent chaos of multiple styles can become a ladder: style can locate the unseen target domain among source domains and guide which domain-dependent prediction rules should be trusted. We propose \emph{Latent Adaptive Domain Disentanglement and Environment Reweighting} (LADDER), a fixed-model DG pipeline that learns causal/style representations, freezes the encoders, fits source-specific classifiers, and uses an unlabeled target-domain covariate set only at inference to compute weights over these fixed classifiers, with no target labels or model-state updates. We establish theoretical guarantees for source reweighting and validate LADDER on simulations, FMoW, and a location-grouped iWildCam protocol, with gains in overall and group-averaged accuracy.
