Causal Discovery and Analysis in Complex Systems

The field of causal discovery and analysis is rapidly advancing, with a focus on developing innovative methods to uncover complex relationships in multi-scale systems. Recent research has emphasized the importance of integrating causal semantics with knowledge graphs, enabling principled causal inference and hypothesis formulation. Another significant direction is the development of robust causal discovery algorithms that can handle latent confounding, unfaithfulness, and mixed data types. Furthermore, there is a growing interest in applying causal analysis to real-world problems, such as identifying adverse drug effects and improving time series imputation. Noteworthy papers include: Reconstructing Brain Causal Dynamics, which leverages causal dynamics for effective fMRI-based subject and task fingerprinting. dcFCI: Robust Causal Discovery, which introduces a nonparametric score to assess a PAG's compatibility with observed data, and Causal Knowledge Graphs, which extends knowledge graphs with formal causal semantics for principled causal inference.

Sources

Reconstructing Brain Causal Dynamics for Subject and Task Fingerprints using fMRI Time-series Data

dcFCI: Robust Causal Discovery Under Latent Confounding, Unfaithfulness, and Mixed Data

Causal knowledge graph analysis identifies adverse drug effects

Causal View of Time Series Imputation: Some Identification Results on Missing Mechanism

Identifying Causal Direction via Variational Bayesian Compression

Density Ratio-based Causal Discovery from Bivariate Continuous-Discrete Data

Built with on top of