English

Ordering-Based Causal Discovery with Reinforcement Learning

Machine Learning 2021-09-16 v4

Abstract

It is a long-standing question to discover causal relations among a set of variables in many empirical sciences. Recently, Reinforcement Learning (RL) has achieved promising results in causal discovery from observational data. However, searching the space of directed graphs and enforcing acyclicity by implicit penalties tend to be inefficient and restrict the existing RL-based method to small scale problems. In this work, we propose a novel RL-based approach for causal discovery, by incorporating RL into the ordering-based paradigm. Specifically, we formulate the ordering search problem as a multi-step Markov decision process, implement the ordering generating process with an encoder-decoder architecture, and finally use RL to optimize the proposed model based on the reward mechanisms designed for~each ordering. A generated ordering would then be processed using variable selection to obtain the final causal graph. We analyze the consistency and computational complexity of the proposed method, and empirically show that a pretrained model can be exploited to accelerate training. Experimental results on both synthetic and real data sets shows that the proposed method achieves a much improved performance over existing RL-based method.

Keywords

Cite

@article{arxiv.2105.06631,
  title  = {Ordering-Based Causal Discovery with Reinforcement Learning},
  author = {Xiaoqiang Wang and Yali Du and Shengyu Zhu and Liangjun Ke and Zhitang Chen and Jianye Hao and Jun Wang},
  journal= {arXiv preprint arXiv:2105.06631},
  year   = {2021}
}

Comments

Accepted to IJCAI'2021

R2 v1 2026-06-24T02:06:07.020Z