论文标题
有效地解开因果关系
Efficiently Disentangle Causal Representations
论文作者
论文摘要
本文提出了一种有效的方法，可以根据原始分布和新分布中条件概率的差异，并具有因果机制的学习分解表示。我们近似于模型的概括能力的差异，以便它适合标准的机器学习框架，并且可以有效地计算。与依赖于学习者对新分布的适应速度的最新方法相反，所提出的方法仅需要评估模型的概括能力。我们为提出方法的优势提供了理论上的解释，我们的实验表明，所提出的技术为1.9---11.0 $ \ times $ $ hemplie的效率更高，并且比以前在各种任务上的方法快9.4---32.4倍。源代码可在\ url {https://github.com/yuanpeng16/edcr}中获得。
This paper proposes an efficient approach to learning disentangled representations with causal mechanisms based on the difference of conditional probabilities in original and new distributions. We approximate the difference with models' generalization abilities so that it fits in the standard machine learning framework and can be efficiently computed. In contrast to the state-of-the-art approach, which relies on the learner's adaptation speed to new distribution, the proposed approach only requires evaluating the model's generalization ability. We provide a theoretical explanation for the advantage of the proposed method, and our experiments show that the proposed technique is 1.9--11.0$\times$ more sample efficient and 9.4--32.4 times quicker than the previous method on various tasks. The source code is available at \url{https://github.com/yuanpeng16/EDCR}.
