论文标题
通过分布匹配的不变因果机制
Invariant Causal Mechanisms through Distribution Matching
论文作者
论文摘要
捕获基本数据生成过程的学习表示是对神经网络有效和强大使用的关键问题。鲁棒性的一个关键特性应捕获，并且最近受到了很多关注的概念，它是通过不变性的概念来描述的。在这项工作中，我们为学习不变表示形式提供了一种因果观点和新算法。从经验上讲，我们证明该算法在各种任务中都很好地运作，尤其是我们观察到域概括的最新性能，在该任务上，我们能够显着提高现有模型的分数。
Learning representations that capture the underlying data generating process is a key problem for data efficient and robust use of neural networks. One key property for robustness which the learned representation should capture and which recently received a lot of attention is described by the notion of invariance. In this work we provide a causal perspective and new algorithm for learning invariant representations. Empirically we show that this algorithm works well on a diverse set of tasks and in particular we observe state-of-the-art performance on domain generalization, where we are able to significantly boost the score of existing models.
