Prediction models for network-linked data

Abstract

Prediction algorithms typically assume the training data are independent samples, but in many modern applications samples come from individuals connected by a network. For example, in adolescent health studies of risk-taking behaviors, information on the subjects' social network is often available and plays an important role through network cohesion, the empirically observed phenomenon of friends behaving similarly. Taking cohesion into account in prediction models should allow us to improve their performance. Here we propose a network-based penalty on individual node effects to encourage similarity between predictions for linked nodes, and show that incorporating it into prediction leads to improvement over traditional models both theoretically and empirically when network cohesion is present. The penalty can be used with many loss-based prediction methods, such as regression, generalized linear models, and Cox's proportional hazard model. Applications to predicting levels of recreational activity and marijuana usage among teenagers from the AddHealth study based on both demographic covariates and friendship networks are discussed in detail and show that our approach to taking friendships into account can significantly improve predictions of behavior while providing interpretable estimates of covariate effects.

References in corpus (4)

• Structure and inference in annotated networks
• Variable selection and regression analysis for graph-structured covariates with an application to genomics
• Empirical stationary correlations for semi-supervised learning on graphs
• Taking advantage of hybrid systems for sparse direct solvers via task-based runtimes

Cited by in corpus (6)

• Group-driven Reinforcement Learning for Personalized mHealth Intervention
• Learning from weakly dependent data under Dobrushin's condition
• Going off the Grid: Iterative Model Selection for Biclustered Matrix Completion
• Regression from Dependent Observations
• Edge sampling using network local information
• Bayesian Network Regularized Regression for Modeling Urban Crime Occurrences