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.
翻译:然而,独立因果机制的原则(ICM、Peters等人(2017年))可以将这一弱点变为一个机会:在培训期间,可以利用不同环境之间的分配变化,以获得更强有力的模式。我们提议一个新的基于梯度的学习框架,其客观功能来自ICM原则。我们从理论上和实验上表明,在这一框架中培训的神经网络侧重于环境之间始终没有变化的关系,而忽视不稳定的关系。此外,我们证明,在某些条件下,恢复的稳定关系与真正的因果机制相对应。在回归和分类方面,由此产生的模式都很好地概括了传统培训模式失败的未知情景。