Graph Coding for Model Selection and Anomaly Detection in Gaussian Graphical Models
This work provides a more rigorous approach for graph model selection and anomaly detection in Gaussian graphical models, which is beneficial for researchers and practitioners working with complex interacting variables.
This paper extends description length for data analysis in Gaussian graphical models, moving beyond simple model selection and scalar sequences. The method utilizes universal graph coding to rigorously account for model complexity, demonstrating improved performance over common methods in identifying graph models and anomalies in synthetic and ECG data.
A classic application of description length is for model selection with the minimum description length (MDL) principle. The focus of this paper is to extend description length for data analysis beyond simple model selection and sequences of scalars. More specifically, we extend the description length for data analysis in Gaussian graphical models. These are powerful tools to model interactions among variables in a sequence of i.i.d Gaussian data in the form of a graph. Our method uses universal graph coding methods to accurately account for model complexity, and therefore provide a more rigorous approach for graph model selection. The developed method is tested with synthetic and electrocardiogram (ECG) data to find the graph model and anomaly in Gaussian graphical models. The experiments show that our method gives better performance compared to commonly used methods.