Estimation of a Causal Directed Acyclic Graph Process using Non-Gaussianity
This is an incremental improvement for researchers in causal inference and machine learning dealing with complex time-series data.
The paper tackles the problem of high parameter count in VAR-LiNGAM for causal discovery by proposing CGP-LiNGAM, which reduces parameters and uses a single causal graph, achieving significant parameter reduction.
Numerous approaches have been proposed to discover causal dependencies in machine learning and data mining; among them, the state-of-the-art VAR-LiNGAM (short for Vector Auto-Regressive Linear Non-Gaussian Acyclic Model) is a desirable approach to reveal both the instantaneous and time-lagged relationships. However, all the obtained VAR matrices need to be analyzed to infer the final causal graph, leading to a rise in the number of parameters. To address this issue, we propose the CGP-LiNGAM (short for Causal Graph Process-LiNGAM), which has significantly fewer model parameters and deals with only one causal graph for interpreting the causal relations by exploiting Graph Signal Processing (GSP).