Prediction models for network-linked data

DOI10.1214/18-AOAS1205zbMATH Open1417.62354arXiv1602.01192MaRDI QIDQ2415451FDOQ2415451

Authors: Tianxi Li, Elizaveta Levina, Ji Zhu 

Publication date: 22 May 2019

Published in: The Annals of Applied Statistics (Search for Journal in Brave)

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.

Full work available at URL: https://arxiv.org/abs/1602.01192

Recommendations

• A dynamic logistic regression for network link prediction
• Network regression with predictive clustering trees
• Logistic regression with network structure
• Incorporating Predictor Network in Penalized Regression with Application to Microarray Data
• Network models for social influence processes

zbMATH Keywords

predictionregressionnetwork cohesion

Mathematics Subject Classification ID

Multivariate analysis (62H99) Estimation in multivariate analysis (62H12) Applications of statistics to social sciences (62P25)

Cited In (18)

• Bayesian reconstruction of Cartesian product graph signals with general patterns of missing data
• Subset selection in network-linked data
• Multiclass analysis and prediction with network structured covariates
• Joint modeling of playing time and purchase propensity in massively multiplayer online role-playing games using crossed random effects
• A Bayesian approach for subgroup analysis
• Spatial Tweedie exponential dispersion models: an application to insurance rate-making
• Network vector autoregression with individual effects
• Network regression with predictive clustering trees
• Detecting clusters in multivariate response regression
• Logistic regression with network structure
• High-dimensional Gaussian graphical models on network-linked data
• Depth-based classification for relational data with multiple attributes
• A note on a dynamic network model with homogeneous structure
• Integrating graph structures into kernel regression models
• Bayesian spatial homogeneous regression
• A Unifying Generative Model for Graph Learning Algorithms: Label Propagation, Graph Convolutions, and Combinations
• Modeling urban crime occurrences via network regularized regression
• Prediction models with graph kernel regularization for network data

This page was built for publication: Prediction models for network-linked data

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2415451)