Disentangled representation learning aims to learn a low dimensional representation of data where each dimension corresponds to one underlying generative factor. Due to the causal relationships between generative factors in real-world situations, causal disentangled representation learning has received widespread attention. In this paper, we first propose a variant of autoregressive flows, called causal flows, which incorporate true causal structure of generative factors into the flows. Then, we design a new VAE model based on causal flows named Causal Flows Variational Autoencoders (CauF-VAE) to learn causally disentangled representations. We provide a theoretical analysis of the disentanglement identifiability of CauF-VAE by incorporating supervised information on the ground-truth factors. The performance of CauF-VAE is evaluated on both synthetic and real datasets, showing its capability of achieving causal disentanglement and performing intervention experiments. Moreover, CauF-VAE exhibits remarkable performance on downstream tasks and has the potential to learn true causal structure among factors.

翻译：解耦表示学习旨在学习数据的低维表示，其中每个维度对应一个潜在生成因子。由于现实场景中生成因子之间存在因果关系，因果解耦表示学习受到广泛关注。本文首先提出一种自回归流的变体——因果流，该结构将生成因子的真实因果结构融入流模型中。随后，我们基于因果流设计了一种新的VAE模型，命名为因果流变分自编码器（CauF-VAE），用于学习因果解耦表示。通过引入真实因子的监督信息，我们对CauF-VAE的解耦可识别性进行了理论分析。在合成数据集与真实数据集上的实验表明，CauF-VAE能够实现因果解耦并执行干预实验。此外，CauF-VAE在下游任务中展现出卓越性能，并具备学习因子间真实因果结构的潜力。