Domain generalization (DG) aims to learn predictive models that can generalize to unseen domains. Most existing DG approaches focus on learning domain-invariant representations under the assumption of conditional distribution shift (i.e., primarily addressing changes in $P(X\mid Y)$ while assuming $P(Y)$ remains stable). However, real-world scenarios with multiple domains often involve compound distribution shifts where both the marginal label distribution $P(Y)$ and the conditional distribution $P(X\mid Y)$ vary simultaneously. To address this, we propose a unified framework for robust domain generalization under divergent marginal and conditional distributions. We derive a novel risk bound for unseen domains by explicitly decomposing the joint distribution into marginal and conditional components and characterizing risk gaps arising from both sources of divergence. To operationalize this bound, we design a meta-learning procedure that minimizes and validates the proposed risk bound across seen domains, ensuring strong generalization to unseen ones. Empirical evaluations demonstrate that our method achieves state-of-the-art performance not only on conventional DG benchmarks but also in challenging multi-domain long-tailed recognition settings where both marginal and conditional shifts are pronounced.

翻译：域泛化（Domain Generalization，DG）旨在学习能够泛化到未见域的预测模型。现有的大多数DG方法侧重于在条件分布偏移假设下学习域不变表示（即主要处理$P(X\mid Y)$的变化，同时假设$P(Y)$保持稳定）。然而，现实世界中涉及多域的场景通常存在复合分布偏移，即边缘标签分布$P(Y)$和条件分布$P(X\mid Y)$同时发生变化。为解决这一问题，我们提出了一个在发散的边缘分布与条件分布下实现鲁棒域泛化的统一框架。通过显式地将联合分布分解为边缘分量与条件分量，并刻画由两种发散源引起的风险间隙，我们推导出一个针对未见域的新风险界。为实现该风险界的优化，我们设计了一种元学习过程，该过程在已见域上最小化并验证所提出的风险界，从而确保对未见域具备强大的泛化能力。实证评估表明，我们的方法不仅在传统DG基准测试上取得了最先进的性能，而且在边缘偏移与条件偏移均显著的、具有挑战性的多域长尾识别场景中同样表现优异。