A1368
Title: Network propagation regression: A general and interpretable framework for network-linked data
Authors: Yingying Ma - Beihang University (China) [presenting]
Chenlei Leng - University of Warwick (United Kingdom)
Abstract: Network linked data are increasingly common in the social, biological, and information sciences, yet classical regression methods often fail to account for dependencies induced by network structure. A unified and interpretable framework for regression on network linked data--network propagation regression (NPR)--is proposed that flexibly captures both direct and higher-order network effects across diverse outcome types. NPR enables simple and efficient estimation via ordinary least squares for continuous outcomes and standard generalized linear model routines for binary, categorical, and time-to-event data. Consistency and asymptotic normality of the estimators under weak conditions are established, and hypothesis tests for the effective order of network influence are developed. Simulations demonstrate that NPR outperforms established methods, particularly under model misspecification. An application to social media sentiment analysis illustrates the practical utility and robustness of NPR. The framework provides a principled and general solution for regression analysis in complex networks.
