TY - JOUR
T1 - Incorporating structural constraints into continuous optimization for causal discovery
AU - Wang, Zidong
AU - Gao, Xiaoguang
AU - Liu, Xiaohan
AU - Ru, Xinxin
AU - Zhang, Qingfu
N1 - Publisher Copyright:
© 2024 Elsevier B.V.
PY - 2024/8/28
Y1 - 2024/8/28
N2 - Directed Acyclic Graphs (DAGs) provide an efficient framework to describe the causal relations in actual applications, and it appears more and more important to learn a DAG from training data in causal discovery. Recently, a novel methodology, which projects the acyclic constraints by an algebraic characterization and employs continuous optimization to carry the causal discovery, gradually became the mainstream. However, such methods focus on a best-fitting to the training data and cannot utilize the prior knowledge in an efficient way. To resolve this problem, we suggest incorporating structural constraints into continuous optimization. For edge constraints, we regard the activation value of the difference between the constraint matrix after thresholding and the weight matrix as the optimization goal. For path constraints, we use the deviation concluded from the power matrix on kth path graphs to design the penalty functions. For ordering constraints, we exploit the representation based on the negative edge/path constraints. The mathematical derivations prove that equality constraint program (ECP), in which proposed equality constraints powerfully embody the required structural restrictions, are solvable. Furthermore, the experimental evaluations indicate that the proposed method develops higher scalability and accuracy against state-of-the-art algorithms.
AB - Directed Acyclic Graphs (DAGs) provide an efficient framework to describe the causal relations in actual applications, and it appears more and more important to learn a DAG from training data in causal discovery. Recently, a novel methodology, which projects the acyclic constraints by an algebraic characterization and employs continuous optimization to carry the causal discovery, gradually became the mainstream. However, such methods focus on a best-fitting to the training data and cannot utilize the prior knowledge in an efficient way. To resolve this problem, we suggest incorporating structural constraints into continuous optimization. For edge constraints, we regard the activation value of the difference between the constraint matrix after thresholding and the weight matrix as the optimization goal. For path constraints, we use the deviation concluded from the power matrix on kth path graphs to design the penalty functions. For ordering constraints, we exploit the representation based on the negative edge/path constraints. The mathematical derivations prove that equality constraint program (ECP), in which proposed equality constraints powerfully embody the required structural restrictions, are solvable. Furthermore, the experimental evaluations indicate that the proposed method develops higher scalability and accuracy against state-of-the-art algorithms.
KW - Causal discovery
KW - Constraints
KW - Continuous optimization
KW - Directed acyclic graphs
UR - http://www.scopus.com/inward/record.url?scp=85194341765&partnerID=8YFLogxK
U2 - 10.1016/j.neucom.2024.127902
DO - 10.1016/j.neucom.2024.127902
M3 - 文章
AN - SCOPUS:85194341765
SN - 0925-2312
VL - 595
JO - Neurocomputing
JF - Neurocomputing
M1 - 127902
ER -