Hybrids of Constraint-based and Noise-based Algorithms for Causal Discovery from Time Series - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2023

Hybrids of Constraint-based and Noise-based Algorithms for Causal Discovery from Time Series

Résumé

Constraint-based and noise-based methods have been proposed to discover summary causal graphs from observational time series under strong assumptions which can be violated or impossible to verify in real applications. Recently, a hybrid method (Assaad et al, 2021) that combines these two approaches, proved to be robust to assumption violation. However, this method assumes that the summary causal graph is acyclic, but cycles are common in many applications. For example, in ecological communities, there may be cyclic relationships between predator and prey populations, creating feedback loops. Therefore, this paper presents two new frameworks for hybrids of constraint-based and noise-based methods that can discover summary causal graphs that may or may not contain cycles. For each framework, we provide two hybrid algorithms which are experimentally tested on simulated data, realistic ecological data, and real data from various applications. Experiments show that our hybrid approaches are robust and yield good results over most datasets.

Dates et versions

hal-04500481 , version 1 (12-03-2024)

Licence

Paternité

Identifiants

Citer

Charles K. Assaad, Daria Bystrova, Julyan Arbel, Emilie Devijver, Eric Gaussier, et al.. Hybrids of Constraint-based and Noise-based Algorithms for Causal Discovery from Time Series. 2023. ⟨hal-04500481⟩
10 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More