Local graph estimation with pathwise false discovery control

TL;DR

This paper introduces local graph estimation using pathwise feature selection (PFS), which accurately infers local network structures around target variables with false discovery control across diverse scientific fields.

Contribution

The paper presents PFS, a new method for local graph estimation that improves interpretability and provides finite-sample false discovery control in complex data settings.

Findings

PFS effectively recovers local structures in various applications.

PFS maintains rigorous false discovery control.

Applications demonstrate interpretability and consistency with domain knowledge.

Abstract

Many datasets include a small set of variables, such as biomarkers or clinical outcomes, whose relationships to the broader system are of primary scientific interest. Estimating the full network of inter-variable relationships in such settings often obscures local structures around these targets, limiting interpretability. To address this fundamental problem, we introduce local graph estimation, a statistical framework for inferring substructures around target variables. We show that traditional graph estimation methods often fail to recover local structure, and present pathwise feature selection (PFS) as an effective alternative. PFS estimates local subgraphs by iteratively applying feature selection and propagating uncertainty along network paths, providing rigorous finite-sample false discovery control even in settings with mixed variable types and nonlinear dependencies. In four distinct applications spanning environmental and public health, multiomics, brain connectomics, and single-nucleus RNA sequencing, PFS recovers interpretable networks consistent with domain knowledge, highlighting its ability to uncover established mechanisms and generate novel hypotheses.