» Articles » PMID: 38921230

Choice Function-Based Hyper-Heuristics for Causal Discovery Under Linear Structural Equation Models

Overview
Date 2024 Jun 26
PMID 38921230
Authors
Affiliations
Soon will be listed here.
Abstract

Causal discovery is central to human cognition, and learning directed acyclic graphs (DAGs) is its foundation. Recently, many nature-inspired meta-heuristic optimization algorithms have been proposed to serve as the basis for DAG learning. However, a single meta-heuristic algorithm requires specific domain knowledge and empirical parameter tuning and cannot guarantee good performance in all cases. Hyper-heuristics provide an alternative methodology to meta-heuristics, enabling multiple heuristic algorithms to be combined and optimized to achieve better generalization ability. In this paper, we propose a multi-population choice function hyper-heuristic to discover the causal relationships encoded in a DAG. This algorithm provides a reasonable solution for combining structural priors or possible expert knowledge with swarm intelligence. Under a linear structural equation model (SEM), we first identify the partial v-structures through partial correlation analysis as the structural priors of the next nature-inspired swarm intelligence approach. Then, through partial correlation analysis, we can limit the search space. Experimental results demonstrate the effectiveness of the proposed methods compared to the earlier state-of-the-art methods on six standard networks.

Citing Articles

A Novel Hyper-Heuristic Algorithm with Soft and Hard Constraints for Causal Discovery Using a Linear Structural Equation Model.

Dang Y, Gao X, Wang Z Entropy (Basel). 2025; 27(1).

PMID: 39851658 PMC: 11764665. DOI: 10.3390/e27010038.

References
1.
Corander J, Hanage W, Pensar J . Causal discovery for the microbiome. Lancet Microbe. 2022; 3(11):e881-e887. PMC: 9680137. DOI: 10.1016/S2666-5247(22)00186-0. View

2.
Larsson S, Butterworth A, Burgess S . Mendelian randomization for cardiovascular diseases: principles and applications. Eur Heart J. 2023; 44(47):4913-4924. PMC: 10719501. DOI: 10.1093/eurheartj/ehad736. View

3.
Chen O, Bodelet J, Saraiva R, Phan H, Di J, Nagels G . The roles, challenges, and merits of the p value. Patterns (N Y). 2023; 4(12):100878. PMC: 10724370. DOI: 10.1016/j.patter.2023.100878. View

4.
Lee H, Danieletto M, Miotto R, Cherng S, Dudley J . Scaling structural learning with NO-BEARS to infer causal transcriptome networks. Pac Symp Biocomput. 2019; 25:391-402. View

5.
Drake J, Ozcan E, Burke E . A Case Study of Controlling Crossover in a Selection Hyper-heuristic Framework Using the Multidimensional Knapsack Problem. Evol Comput. 2015; 24(1):113-41. DOI: 10.1162/EVCO_a_00145. View