Cai Ruichu, Qiao Jie, Zhang Kun, Zhang Zhenjie, Hao Zhifeng
School of Computer Science, Guangdong University of Technology, China.
Department of philosophy, Carnegie Mellon University.
Adv Neural Inf Process Syst. 2018 Dec;2018:2666-2674.
Causal discovery from a set of observations is one of the fundamental problems across several disciplines. For continuous variables, recently a number of causal discovery methods have demonstrated their effectiveness in distinguishing the cause from effect by exploring certain properties of the conditional distribution, but causal discovery on categorical data still remains to be a challenging problem, because it is generally not easy to find a compact description of the causal mechanism for the true causal direction. In this paper we make an attempt to find a way to solve this problem by assuming a two-stage causal process: the first stage maps the cause to a hidden variable of a lower cardinality, and the second stage generates the effect from the hidden representation. In this way, the causal mechanism admits a simple yet compact representation. We show that under this model, the causal direction is identifiable under some weak conditions on the true causal mechanism. We also provide an effective solution to recover the above hidden compact representation within the likelihood framework. Empirical studies verify the effectiveness of the proposed approach on both synthetic and real-world data.
从一组观测数据中发现因果关系是多个学科的基本问题之一。对于连续变量，最近一些因果发现方法通过探索条件分布的某些属性，在区分因果关系方面展示了其有效性。但对于分类数据的因果发现仍然是一个具有挑战性的问题，因为通常很难找到一个简洁的关于真实因果方向的因果机制描述。在本文中，我们尝试通过假设一个两阶段因果过程来找到解决这个问题的方法：第一阶段将原因映射到一个较低基数的隐藏变量，第二阶段从隐藏表示中生成结果。通过这种方式，因果机制允许一个简单而紧凑的表示。我们表明，在这个模型下，在关于真实因果机制的一些弱条件下，因果方向是可识别的。我们还提供了一种在似然框架内恢复上述隐藏紧凑表示的有效解决方案。实证研究验证了所提出方法在合成数据和真实世界数据上的有效性。
