We consider the problem of answering observational, interventional, and counterfactual queries in a causally sufficient setting where only observational data and the causal graph are available. Utilizing the recent developments in diffusion models, we introduce diffusion-based causal models (DCM) to learn causal mechanisms, that generate unique latent encodings. These encodings enable us to directly sample under interventions and perform abduction for counterfactuals. Diffusion models are a natural fit here, since they can encode each node to a latent representation that acts as a proxy for exogenous noise. Our empirical evaluations demonstrate significant improvements over existing state-of-the-art methods for answering causal queries. Furthermore, we provide theoretical results that offer a methodology for analyzing counterfactual estimation in general encoder-decoder models, which could be useful in settings beyond our proposed approach.

翻译：我们考虑在因果充分设定下，仅利用观测数据和因果图来回答观测性、干预性和反事实查询的问题。借助扩散模型的最新进展，我们引入基于扩散的因果模型（DCM）来学习因果机制，从而生成独特的潜在编码。这些编码使我们能够在干预条件下直接采样，并执行用于反事实推断的溯因推理。扩散模型在此处具有天然适配性，因为它们能将每个节点编码为作为外生噪声代理的潜在表示。我们的实证评估表明，该方法在回答因果查询方面显著优于现有最先进方法。此外，我们提供的理论结果建立了一种分析通用编码器-解码器模型中反事实估计的方法论，这可能在超出本文所提方法的场景中具有实用性。