ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Distinguish Markov Equivalence Classes from Large-Scale Linear Non-Gaussian Data

Mai, Guizhen; Hong, Yinghan*; Chen, Pinghua; Chen, Kexi; Huang, Han; Zheng, Gengzhong广东工业大学; 韩山师范学院
IEEE Access2020DOI: 10.1109/ACCESS.2020.2965093
1被引10阅读
引用收藏
分享

摘要

In the problem of causal discovery, conditional independence (CI) tests are generally used to detect the causal relationships among observed data. Due to the curse of dimensionality and the limitation of causal direction learning based on V-structure learning, it is difficult for constraint-based methods to distinguish the actual graph from a set of Markov equivalence classes. To alleviate this problem, in this work, a novel regression-based method to test CIs over linear Non-Gaussian data is proposed. The main purpose of this proposal is to relax the CI test of x vertical bar y vertical bar Z to two unconditional independence tests x = f(Z)perpendicular to y g (Z) + Sigma H (Z) and x - f(Z) + Sigma H (Z)perpendicular to y - g (Z), where f and g can be estimated by linear regression independently. In addition, we further show that x-f/perpendicular to y-g (Z)+Sigma H (Z) (or x-f (Z) + Sigma H (Z)perpendicular to y- g (Z) ) can lead to x <- Z (or y <- Z). According to this regression-based method, we design a causal structure learning algorithm to learn the actual graph instead of a set of Markov equivalence classes over the observed data. Experiments indicate that our method can detect much more causal relationships than other existing methods, especially in large-scale cases.

学科与关键词

关键词
Causal inferencelinear non-Gaussian additive noise modelMarkova equivalence classes
相关
加载中…
  • A Distribution Free Conditional Independence Test with Applications to Causal Discovery
    Cai, Zhanrui*; Li, Runze; Zhang, YaowuJOURNAL OF MACHINE LEARNING RESEARCH, 2022, 23.
  • Towards Efficient Local Causal Structure Learning
    Yang, Shuai; Wang, Hao; Yu, Kui*; Cao, Fuyuan; Wu, XindongIEEE Transactions on Big Data, 2022, 8(6): 1592-1609.被引 8
  • Learning linear non-Gaussian directed acyclic graph with diverging number of nodes
    Zhao, Ruixuan*; He, Xin; Wang, JunhuiJOURNAL OF MACHINE LEARNING RESEARCH, 2022, 23.
查看全部 →

发表信息

论文状态
公开发表
期刊
IEEE Access
发表日期
2020
卷期
第 8 卷
页码
10924-10932
DOI
10.1109/ACCESS.2020.2965093
语言
ENGLISH
期刊收录
NSL.SCIE
期刊等级
3区
成果收录
SCIE
资助标注
National Natural Science Foundation of China [61572144, 61976052, 61876207, 61973092]; Guangdong Natural Science Funds for Distinguished Young Scholar [2014A030306050]; Science and Technology Planning Project of Guangdong Province, China [2017A040405063, 2017B030307002, 2019B101001021, 2015B090922014, 2015A010103015]; Hanshan Normal University Doctor Starting Fund [QD20190628]; Hanshan Normal University Scientific Research Talents Fund [Z19113]; Science and Technology Planning Project of Tianhe District, Guangzhou City, Guangdong Province [201703YG029]; International Cooperation Project of Guangzhou [201807010047]; Guangzhou Science and Technology Project [201802010007, 201804010276]; Guangdong Province Key Area Research and Development Program [2018B010109003]

作者

  • M

    Mai, Guizhen (第一作者)

    guangdong univ technol

  • H

    Hong, Yinghan (通讯)

    hanshan normal univ

查看全部 6 位作者收起作者
  • C

    Chen, Pinghua

    guangdong univ technol

  • C

    Chen, Kexi

    guangdong univ technol

  • H

    Huang, Han

  • Z

    Zheng, Gengzhong

    hanshan normal univ

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417