Network Regression with Graph Laplacians

TL;DR

This paper extends regression analysis to network data using graph Laplacians and Fréchet means, enabling the study of how networks relate to covariates with proven asymptotic properties.

Contribution

It introduces a novel Fréchet regression framework for networks based on graph Laplacians, with theoretical justification and practical validation.

Findings

Good practical performance in simulations

Effective analysis of neuroimaging network data

Accurate modeling of network dependence on covariates

Abstract

Network data are increasingly available in various research fields, motivating statistical analysis for populations of networks where a network as a whole is viewed as a data point. Due to the non-Euclidean nature of networks, basic statistical tools available for scalar and vector data are no longer applicable when one aims to relate networks as outcomes to Euclidean covariates, while the study of how a network changes in dependence on covariates is often of paramount interest. This motivates to extend the notion of regression to the case of responses that are network data. Here we propose to adopt conditional Fr\'{e}chet means implemented with both global least squares regression and local weighted least squares smoothing, extending the Fr\'{e}chet regression concept to networks that are quantified by their graph Laplacians. The challenge is to characterize the space of graph Laplacians so as to justify the application of Fr\'{e}chet regression. This characterization then leads to asymptotic rates of convergence for the corresponding M-estimators by applying empirical process methods. We demonstrate the usefulness and good practical performance of the proposed framework with simulations and with network data arising from resting-state fMRI in neuroimaging, as well as New York taxi records.