arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.03009cs.AIcs.LG
收藏

基于深度强化学习的因果结构主动学习

Active Learning of Causal Structures with Deep Reinforcement Learning

Sharif University of Technology(谢里夫理工大学)

Amir Amirinezhad, Saber Salehkaleybar, Matin Hashemi

摘要:

我们研究实验设计问题,以从干预数据中学习因果结构。我们考虑一个主动学习的设置,其中实验者决定干预系统中的变量之一,在每一步,并使用干预的结果,以恢复变量之间的进一步的因果关系。目标是以最少的干预措施充分识别因果结构。我们提出了第一个基于深度强化学习的实验设计问题解决方案。在所提出的方法中,我们使用一个图神经网络将输入图嵌入到向量中,并将它们馈送到另一个神经网络,该神经网络输出一个变量,用于在每一步中进行干预。两个网络通过Q迭代算法联合训练。实验结果表明,该方法在恢复因果结构方面取得了有竞争力的性能,同时显着减少密集图中的执行时间。

英文摘要:

We study the problem of experiment design to learn causal structures from interventional data. We consider an active learning setting in which the experimenter decides to intervene on one of the variables in the system in each step and uses the results of the intervention to recover further causal relationships among the variables. The goal is to fully identify the causal structures with minimum number of interventions. We present the first deep reinforcement learning based solution for the problem of experiment design. In the proposed method, we embed input graphs to vectors using a graph neural network and feed them to another neural network which outputs a variable for performing intervention in each step. Both networks are trained jointly via a Q-iteration algorithm. Experimental results show that the proposed method achieves competitive performance in recovering causal structures with respect to previous works, while significantly reducing execution time in dense graphs.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑