Sound and complete algorithms have been proposed to compute identifiable causal queries using the causal structure and data. However, most of these algorithms assume accurate estimation of the data distribution, which is impractical for high-dimensional variables such as images. On the other hand, modern deep generative architectures can be trained to sample from high-dimensional distributions. However, training these networks are typically very costly. Thus, it is desirable to leverage pre-trained models to answer causal queries using such high-dimensional data. To address this, we propose modular training of deep causal generative models that not only makes learning more efficient, but also allows us to utilize large, pre-trained conditional generative models. To the best of our knowledge, our algorithm, Modular-DCM is the first algorithm that, given the causal structure, uses adversarial training to learn the network weights, and can make use of pre-trained models to provably sample from any identifiable causal query in the presence of latent confounders. With extensive experiments on the Colored-MNIST dataset, we demonstrate that our algorithm outperforms the baselines. We also show our algorithm's convergence on the COVIDx dataset and its utility with a causal invariant prediction problem on CelebA-HQ.

翻译：已有研究提出完备且可靠的算法，利用因果结构与数据计算可识别的因果查询。然而，这些算法大多假设数据分布能被准确估计，这对于图像等高维变量而言并不现实。另一方面，现代深度生成架构能够通过训练从高维分布中采样，但训练此类网络通常成本极高。因此，如何利用预训练模型基于此类高维数据回答因果查询成为重要课题。为此，我们提出深度因果生成模型的模块化训练方法，该方法不仅能提升学习效率，还可充分利用大规模预训练条件生成模型。据我们所知，我们提出的Modular-DCM算法是首个在给定因果结构的条件下，采用对抗训练学习网络权重，并能利用预训练模型在存在潜在混杂因素的情况下可证明地从任意可识别因果查询中采样的算法。通过在Colored-MNIST数据集上的大量实验，我们证明该算法优于现有基线方法。我们还在COVIDx数据集上展示了算法的收敛性，并通过CelebA-HQ上的因果不变性预测问题验证了其实用价值。