Decomposing causality into its synergistic, unique, and redundant components

Causality lies at the heart of scientific inquiry, serving as the fundamental basis for understanding interactions among variables in physical systems. Despite its central role, current methods for causal inference face significant challenges due to nonlinear dependencies, stochastic interactions, s...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Nature communications Jg. 15; H. 1; S. 9296 - 15
Hauptverfasser: Martínez-Sánchez, Álvaro, Arranz, Gonzalo, Lozano-Durán, Adrián
Format: Journal Article
Sprache:Englisch
Veröffentlicht: London Nature Publishing Group UK 01.11.2024
Nature Publishing Group
Springer Science and Business Media LLC
Nature Portfolio
Schlagworte:
631/553/2393
631/553/2701
639/705/1041
639/766/189
639/766/259
applied mathematics
Causality
Complex systems
Decomposition
dynamical systems
fluid dynamics
Humanities and Social Sciences
Inference
information theory and computation
multidisciplinary
Nonlinear systems
Redundant components
Science
Science (multidisciplinary)
time series
ISSN:2041-1723, 2041-1723
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Causality lies at the heart of scientific inquiry, serving as the fundamental basis for understanding interactions among variables in physical systems. Despite its central role, current methods for causal inference face significant challenges due to nonlinear dependencies, stochastic interactions, self-causation, collider effects, and influences from exogenous factors, among others. While existing methods can effectively address some of these challenges, no single approach has successfully integrated all these aspects. Here, we address these challenges with SURD: Synergistic-Unique-Redundant Decomposition of causality. SURD quantifies causality as the increments of redundant, unique, and synergistic information gained about future events from past observations. The formulation is non-intrusive and applicable to both computational and experimental investigations, even when samples are scarce. We benchmark SURD in scenarios that pose significant challenges for causal inference and demonstrate that it offers a more reliable quantification of causality compared to previous methods. The methods for detection of cause-effect interactions in complex systems face challenges in the presence of nonlinear dependencies or stochastic interactions. The authors propose a framework for decomposition of causality into redundant, unique, and synergistic contributions, providing a measure of the causality from multiple or hidden system variables.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
USDOE National Nuclear Security Administration (NNSA)
NA0003993
ISSN:2041-1723
2041-1723
DOI:10.1038/s41467-024-53373-4