TY - JOUR
T1 - Dynamic network reconstruction from heterogeneous datasets
AU - Yue, Zuogong
AU - Thunberg, Johan
AU - Pan, Wei
AU - Ljung, Lennart
AU - Gonçalves, Jorge
PY - 2021
Y1 - 2021
N2 - Performing multiple experiments is common when learning internal mechanisms of complex systems. These experiments can include perturbations of parameters or external disturbances. A challenging problem is to efficiently incorporate all collected data simultaneously to infer the underlying dynamic network. This paper addresses the reconstruction of dynamic networks from heterogeneous datasets under the assumption that the underlying networks share the same Boolean structure across all experiments. Parametric models are derived for dynamical structure functions, which describe causal interactions between measured variables. Multiple datasets are integrated into one regression problem with additional demands on group sparsity to assure network sparsity and structure consistency. To acquire structured group sparsity, we propose a sampling-based method, together with extended versions of l1-methods and sparse Bayesian learning. The performance of the proposed methods is benchmarked in numerical simulation. In summary, this paper presents efficient methods on network reconstruction from multiple experiments, and reveals practical experience that could guide applications.
AB - Performing multiple experiments is common when learning internal mechanisms of complex systems. These experiments can include perturbations of parameters or external disturbances. A challenging problem is to efficiently incorporate all collected data simultaneously to infer the underlying dynamic network. This paper addresses the reconstruction of dynamic networks from heterogeneous datasets under the assumption that the underlying networks share the same Boolean structure across all experiments. Parametric models are derived for dynamical structure functions, which describe causal interactions between measured variables. Multiple datasets are integrated into one regression problem with additional demands on group sparsity to assure network sparsity and structure consistency. To acquire structured group sparsity, we propose a sampling-based method, together with extended versions of l1-methods and sparse Bayesian learning. The performance of the proposed methods is benchmarked in numerical simulation. In summary, this paper presents efficient methods on network reconstruction from multiple experiments, and reveals practical experience that could guide applications.
KW - Heterogeneity
KW - Multiple experiments
KW - Network reconstruction
KW - Sparsity
KW - System identification
UR - http://www.scopus.com/inward/record.url?scp=85096700788&partnerID=8YFLogxK
U2 - 10.1016/j.automatica.2020.109339
DO - 10.1016/j.automatica.2020.109339
M3 - Article
AN - SCOPUS:85096700788
SN - 0005-1098
VL - 123
JO - Automatica
JF - Automatica
M1 - 109339
ER -