Deep generative models have shown tremendous capability in data density estimation and data generation from finite samples. While these models have shown impressive performance by learning correlations among features in the data, some fundamental shortcomings are their lack of explainability, tendency to induce spurious correlations, and poor out-of-distribution extrapolation. To remedy such challenges, recent work has proposed a shift toward causal generative models. Causal models offer several beneficial properties to deep generative models, such as distribution shift robustness, fairness, and interpretability. Structural causal models (SCMs) describe data-generating processes and model complex causal relationships and mechanisms among variables in a system. Thus, SCMs can naturally be combined with deep generative models. We provide a technical survey on causal generative modeling categorized into causal representation learning and controllable counterfactual generation methods. We focus on fundamental theory, methodology, drawbacks, datasets, and metrics. Then, we cover applications of causal generative models in fairness, privacy, out-of-distribution generalization, precision medicine, and biological sciences. Lastly, we discuss open problems and fruitful research directions for future work in the field.

翻译：深度生成模型在数据密度估计和有限样本数据生成方面展现出巨大潜力。尽管这些模型通过学习数据特征间的相关性取得了令人瞩目的性能，但其仍存在一些根本性缺陷，包括可解释性不足、易引发伪相关性以及分布外泛化能力较差。为应对这些挑战，近期研究提出了向因果生成模型的范式转变。因果模型为深度生成模型提供了多项有益特性，如分布偏移鲁棒性、公平性和可解释性。结构因果模型（SCMs）描述了数据生成过程，并对系统中变量间的复杂因果关系与机制进行建模。因此，SCMs能够自然地与深度生成模型相结合。本文对因果生成建模进行技术性综述，将其划分为因果表征学习和可控反事实生成方法两大类。我们重点关注基础理论、方法论、局限性、数据集及评估指标。随后，我们探讨因果生成模型在公平性、隐私保护、分布外泛化、精准医学和生物科学等领域的应用。最后，我们讨论该领域未来研究面临的开放性问题与富有前景的研究方向。