论文标题
重复的环境推断不变学习
Repeated Environment Inference for Invariant Learning
论文作者
论文摘要
当环境标签未知时，我们研究不变学习的问题。当贝叶斯最佳条件标签分布在不同环境中相同时，我们将重点放在不变的表示概念上。以前的工作通过最大化不变风险最小化（IRM）框架的罚款来进行环境推理（EI）。 EI步骤使用的参考模型侧重于虚假相关性，以有效地达到良好的环境分区。但是，尚不清楚如何找到这样的参考模型。在这项工作中，我们建议重复EI过程并在先前的EI步骤推断出的\ textit {多数}环境上重复ERM模型。在温和的假设下，我们发现这种迭代过程有助于学习比单步更好地捕获虚假相关性的表示形式。这会导致更好的环境推理和更好的不变学习。我们表明，此方法在合成和现实世界数据集上都优于基准。
We study the problem of invariant learning when the environment labels are unknown. We focus on the invariant representation notion when the Bayes optimal conditional label distribution is the same across different environments. Previous work conducts Environment Inference (EI) by maximizing the penalty term from Invariant Risk Minimization (IRM) framework. The EI step uses a reference model which focuses on spurious correlations to efficiently reach a good environment partition. However, it is not clear how to find such a reference model. In this work, we propose to repeat the EI process and retrain an ERM model on the \textit{majority} environment inferred by the previous EI step. Under mild assumptions, we find that this iterative process helps learn a representation capturing the spurious correlation better than the single step. This results in better Environment Inference and better Invariant Learning. We show that this method outperforms baselines on both synthetic and real-world datasets.
