论文标题
不变学习的环境推论
Environment Inference for Invariant Learning
论文作者
论文摘要
优雅地处理分配变化的学习模型对于研究领域概括，强大的优化和公平性是至关重要的。一个有希望的公式是域不变学习，它标识了学习的关键问题，哪些特征是特定于域特异性的与域 - 不变的。在这一领域的一个重要假设是，将培训示例分配到“域”或“环境”中。我们的重点是不提供此类分区的更常见环境。我们提出了EIIL，这是一个用于域不变学习的一般框架，该框架结合了环境推论，以直接推断出最大程度地吸引下游不变性学习的分区。我们表明，在不使用环境标签的情况下，EIIL在CMNIST基准上的表现优于不变的学习方法，并且在水鸟和民用数据集中的最差群体表现上大大优于ERM。最后，我们在EIIL和算法公平之间建立了联系，这使EIIL能够在公平的预测问题中提高准确性和校准。
Learning models that gracefully handle distribution shifts is central to research on domain generalization, robust optimization, and fairness. A promising formulation is domain-invariant learning, which identifies the key issue of learning which features are domain-specific versus domain-invariant. An important assumption in this area is that the training examples are partitioned into "domains" or "environments". Our focus is on the more common setting where such partitions are not provided. We propose EIIL, a general framework for domain-invariant learning that incorporates Environment Inference to directly infer partitions that are maximally informative for downstream Invariant Learning. We show that EIIL outperforms invariant learning methods on the CMNIST benchmark without using environment labels, and significantly outperforms ERM on worst-group performance in the Waterbirds and CivilComments datasets. Finally, we establish connections between EIIL and algorithmic fairness, which enables EIIL to improve accuracy and calibration in a fair prediction problem.
