Modern machine learning models may be susceptible to learning spurious correlations that hold on average but not for the atypical group of samples. To address the problem, previous approaches minimize the empirical worst-group risk. Despite the promise, they often assume that each sample belongs to one and only one group, which does not allow expressing the uncertainty in group labeling. In this paper, we propose a novel framework PG-DRO, which explores the idea of probabilistic group membership for distributionally robust optimization. Key to our framework, we consider soft group membership instead of hard group annotations. The group probabilities can be flexibly generated using either supervised learning or zero-shot approaches. Our framework accommodates samples with group membership ambiguity, offering stronger flexibility and generality than the prior art. We comprehensively evaluate PG-DRO on both image classification and natural language processing benchmarks, establishing superior performance

翻译：现代机器学习模型可能容易学习出平均、而非非典型样本组别所持有的虚假关联。为了解决这个问题,以往的做法尽量减少了经验中最坏群体的风险。尽管有这一承诺,它们往往假设每个样本属于一个和只有一个组别,这不允许在组别标签上表达不确定性。在本文中,我们提出一个新的PG-DRO框架,探讨分配性强优化的概率群体成员资格概念。我们框架的关键是,我们考虑软群体成员资格,而不是硬群体说明。群体概率可以通过监督的学习或零弹射方法灵活生成。我们的框架包含群体成员模糊性的样本,提供了比先前的艺术更强的灵活性和一般性。我们在图像分类和自然语言处理基准方面全面评价PG-DRO,确定优异性业绩。</s>