Out-of-Distribution (OOD) Generalization aims to learn robust models that generalize well to various environments without fitting to distribution-specific features. Recent studies based on Lottery Ticket Hypothesis (LTH) address this problem by minimizing the learning target to find some of the parameters that are critical to the task. However, in OOD problems, such solutions are suboptimal as the learning task contains severe distribution noises, which can mislead the optimization process. Therefore, apart from finding the task-related parameters (i.e., invariant parameters), we propose Exploring Variant parameters for Invariant Learning (EVIL) which also leverages the distribution knowledge to find the parameters that are sensitive to distribution shift (i.e., variant parameters). Once the variant parameters are left out of invariant learning, a robust subnetwork that is resistant to distribution shift can be found. Additionally, the parameters that are relatively stable across distributions can be considered invariant ones to improve invariant learning. By fully exploring both variant and invariant parameters, our EVIL can effectively identify a robust subnetwork to improve OOD generalization. In extensive experiments on integrated testbed: DomainBed, EVIL can effectively and efficiently enhance many popular methods, such as ERM, IRM, SAM, etc.

翻译：分布外（Out-of-Distribution, OOD）泛化旨在学习鲁棒模型，使其能够在各种环境中良好泛化，而不拟合特定分布的伪特征。基于彩票假说（Lottery Ticket Hypothesis, LTH）的最新研究通过最小化学习目标以寻找任务关键参数来解决该问题。然而，在OOD问题中，由于学习任务包含严重的分布噪声，这些噪声可能误导优化过程，此类解决方案并非最优。因此，除了寻找任务相关参数（即不变参数）外，我们提出了用于不变性学习的变异参数探索方法（Exploring Variant parameters for Invariant Learning, EVIL），该方法同时利用分布知识寻找对分布偏移敏感的参数（即变异参数）。一旦将变异参数排除在不变性学习之外，便能找到对分布偏移具有抵抗力的鲁棒子网络。此外，跨分布相对稳定的参数可被视为不变参数，从而增强不变性学习。通过充分探索变异参数和不变参数，我们的EVIL能有效识别鲁棒子网络，提升OOD泛化性能。在集成测试平台DomainBed上进行的大量实验中，EVIL能够高效且有效地增强多种流行方法，例如ERM、IRM、SAM等。