Abstract
Deep generative models have gained popularity in recent years due to their ability to accurately replicate inherent empirical distributions and yield novel samples. In particular, certain advances are proposed wherein the model engenders data examples following specified attributes. Nevertheless, several challenges still exist and are to be overcome, i.e., difficulty in extrapolating out-of-sample data and insufficient learning of disentangled representations. Structural causal models (SCMs), on the other hand, encapsulate the causal factors that govern a generative process and characterize a generative model based on causal relationships, providing crucial insights for addressing the current obstacles in deep generative models. In this paper, we present a comprehensive survey of Causal deep Generative Models (CGMs), which combine SCMs and deep generative models in a way that boosts several trustworthy properties such as robustness, fairness, and interpretability. We provide an overview of the recent advances in CGMs, categorize them based on generative types, and discuss how causality is introduced into the family of deep generative models. We also explore potential avenues for future research in this field.
Abstract (translated)
深度生成模型近年来变得越来越受欢迎,因为其能够准确地复制固有的经验分布并产生新的样本。特别是,我们提出了某些改进,其中模型根据特定的属性生成数据示例。然而,仍然有几种挑战存在,即难以预测离群值数据和不足学习分离表示的能力。结构因果模型(SCMs)则封装了控制生成过程的主要因果因素,并基于因果关系定义生成模型的特征,为解决深度生成模型中的当前障碍提供了关键见解。在本文中,我们介绍了因果深度生成模型的全面综述,该综述将SCMs和深度生成模型相结合,以提升几个可信的特性,如稳健性、公平性和可解释性。我们总结了CGMs最近的进展,按照生成类型进行分类,并讨论如何将因果关系引入深度生成模型家族。我们还探索了该领域未来研究的潜在途径。
URL
https://arxiv.org/abs/2301.12351
