Efficiently Disentangle Causal Representations

Abstract

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}.

17 pages, 7 figures

References in corpus (5)

• Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
• Distinguishing cause from effect using observational data: methods and benchmarks
• Towards a Definition of Disentangled Representations
• Learning Independent Causal Mechanisms
• Causal Reasoning from Meta-reinforcement Learning