Out-of-distribution (OOD) generalization is indispensable for learning models in the wild, where testing distribution typically unknown and different from the training. Recent methods derived from causality have shown great potential in achieving OOD generalization. However, existing methods mainly focus on the invariance property of causes, while largely overlooking the property of \textit{sufficiency} and \textit{necessity} conditions. Namely, a necessary but insufficient cause (feature) is invariant to distribution shift, yet it may not have required accuracy. By contrast, a sufficient yet unnecessary cause (feature) tends to fit specific data well but may have a risk of adapting to a new domain. To capture the information of sufficient and necessary causes, we employ a classical concept, the probability of sufficiency and necessary causes (PNS), which indicates the probability of whether one is the necessary and sufficient cause. To associate PNS with OOD generalization, we propose PNS risk and formulate an algorithm to learn representation with a high PNS value. We theoretically analyze and prove the generalizability of the PNS risk. Experiments on both synthetic and real-world benchmarks demonstrate the effectiveness of the proposed method. The details of the implementation can be found at the GitHub repository: https://github.com/ymy4323460/CaSN.

翻译：分布外（OOD）泛化是模型在真实环境中学习时不可或缺的能力，此时测试分布通常未知且与训练分布不同。近期源自因果性的方法在实现OOD泛化方面展现出巨大潜力。然而，现有方法主要关注原因的"不变性"属性，却很大程度上忽视了其中的"充分性"与"必要性"条件。具体而言，必要但不充分的原因（特征）虽对分布偏移具有不变性，但可能无法达到所需精度。相比之下，充分但不必要的原因（特征）虽能较好拟合特定数据，但在适应新领域时可能存在风险。为捕捉充分且必要原因的信息，我们采用经典概念——充分必要原因概率（PNS），用以衡量某个因素成为充分必要原因的概率。为将PNS与OOD泛化相关联，我们提出PNS风险并构建相应算法，以学习具备高PNS值的表征。我们从理论上分析并证明了PNS风险的泛化能力。在合成数据集与实际基准上的实验结果表明了该方法的有效性。实现细节可参阅GitHub仓库：https://github.com/ymy4323460/CaSN。