论文标题
使用独立因果机制的原理学习健壮的模型
Learning Robust Models Using The Principle of Independent Causal Mechanisms
论文作者
论文摘要
标准监督的学习在数据分配转移下破裂。但是，独立因果机制的原则（ICM，Peters等人（2017））可以将这种弱点变成一个机会：一个人可以利用训练期间不同环境之间的分布转移，以获得更强大的模型。我们提出了一个新的基于梯度的学习框架，其目标函数源自ICM原理。我们在理论上和实验上表明，在此框架中训练的神经网络集中于在环境之间保持不变的关系而忽略不稳定的关系。此外，我们证明恢复的稳定关系对应于在某些条件下的真实因果机制。在回归和分类中，最终的模型都可以很好地推广到传统训练的模型失败的情况下看不见的情况。
Standard supervised learning breaks down under data distribution shift. However, the principle of independent causal mechanisms (ICM, Peters et al. (2017)) can turn this weakness into an opportunity: one can take advantage of distribution shift between different environments during training in order to obtain more robust models. We propose a new gradient-based learning framework whose objective function is derived from the ICM principle. We show theoretically and experimentally that neural networks trained in this framework focus on relations remaining invariant across environments and ignore unstable ones. Moreover, we prove that the recovered stable relations correspond to the true causal mechanisms under certain conditions. In both regression and classification, the resulting models generalize well to unseen scenarios where traditionally trained models fail.
