A regression framework for studying relationships among attributes under network interference

2024-10-10

AI Summary

This paper addresses the challenge of modeling attribute–network interdependencies under network interference. We propose a unified, interpretable, and scalable joint regression framework grounded in causal inference, which rigorously characterizes the causal dependencies between node attributes and network ties. Methodologically, we introduce the first integration of pseudolikelihood estimation with the minorization–maximization (MM) algorithm for parameter learning in high-dimensional interfered networks, and establish theoretical convergence rates for estimators under single-observation settings. The framework synergizes convex optimization with network causal modeling to balance computational efficiency and statistical rigor. Extensive simulations and an empirical analysis of hate speech on X (July–December 2020) demonstrate substantial improvements in both accuracy and interpretability for estimating interference effects on user attributes and content diffusion.

Technology Category

• Machine Learning: Causal Learning
• Reasoning under Uncertainty: Causality
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

To understand how the interconnected and interdependent world of the twenty-first century operates and make model-based predictions, joint probability models for networks and interdependent outcomes are needed. We propose a comprehensive regression framework for networks and interdependent outcomes with multiple advantages, including interpretability, scalability, and provable theoretical guarantees. The regression framework can be used for studying relationships among attributes of connected units and captures complex dependencies among connections and attributes, while retaining the virtues of linear regression, logistic regression, and other regression models by being interpretable and widely applicable. On the computational side, we show that the regression framework is amenable to scalable statistical computing based on convex optimization of pseudo-likelihoods using minorization-maximization methods. On the theoretical side, we establish convergence rates for pseudo-likelihood estimators based on a single observation of dependent connections and attributes. We demonstrate the regression framework using simulations and an application to hate speech on the social media platform X in the six months preceding the insurrection at the U.S. Capitol on January 6, 2021.

Problem

• Model relationships among attributes under network interference
• Develop interpretable scalable regression for network outcomes
• Analyze dependencies in connected units with theoretical guarantees

Innovation

• Comprehensive regression framework for network relationships
• Scalable convex optimization with pseudo-likelihoods
• Theoretical guarantees for dependent data convergence