融合先验约束的拓扑霍克斯过程格兰杰因果发现算法  

Granger causality discovery algorithm for topological Hawkesprocesses with priori-constraints

作　　者：蔡瑞初[1] 刘跃群 黄正婷 黄晓楷 陈薇[1] 郝志峰[1,2] Cai Ruichu;Liu Yuequn;Huang Zhengting;Huang Xiaokai;Chen Wei;Hao Zhifeng(School of Computer Science,Guangdong University of Technology,Guangzhou 510006,China;College of Science,Shantou University,Shantou Guangdong 515063,China)

机构地区：[1]广东工业大学计算机学院,广州510006 [2]汕头大学理学院,广东汕头515063

出　　处：《计算机应用研究》2022年第6期1668-1672,共5页Application Research of Computers

基　　金：国家自然科学基金资助项目(61876043,61976052)。

摘　　要：离散时序数据的格兰杰因果关系发现算法具有重要应用价值。现有方法主要采用霍克斯过程建模,无法适用于非独立同分布数据和带有时间误差的数据。为此,提出了一种融合先验约束的拓扑霍克斯过程格兰杰因果关系发现算法(PTHP)。首先,使用基于约束的方法筛选出一批显著性水平较高的因果边,提升算法对故障发生时间误差的容忍性;随后,将上一步获取的边作为先验约束融合到拓扑霍克斯过程中,解决序列间的非独立同分布问题。模拟数据和真实数据的实验证明了该方法的有效性,并获得了PCIC 2021因果推理大赛第一名。Granger causality discovery algorithm for discrete-time series data has important application value.The existing methods mainly use Hawkes processes modeling,which can not be applied to non-IID data and data with time-skew errors.Therefore,this paper proposed a Granger causality discovery algorithm(PTHP)for topological Hawkes processes integrating a priori constraints.Firstly,it used the constraint-based method to screen a group of causal edges with a high significance level to improve the tolerance of the algorithm to the fault time-skew errors.Then,the edges obtained in the previous step were fused into the topological Hawkes processes as a priori constraints to solve the non-IID problem between sequences.Experiments on simulated data and real-world data show the effectiveness of this method,and it won first place in PCIC 2021 causal inference competition.

关 键 词：格兰杰因果 拓扑霍克斯过程 因果关系发现 因果关系网络 时间误差 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]