Structure-Aware Optimal Intervention for Rumor Dynamics on Networks: Node-Level, Time-Varying, and Resource-Constrained

2025-10-31

AI Summary

This paper addresses the dynamic suppression of rumor propagation in resource-constrained social networks. Method: We propose a node-level, time-varying optimal intervention framework grounded in optimal control theory, jointly incorporating network topology and epidemic dynamics to compute time-dependent control weights under budget constraints. Crucially, we design a phase-aware strategy: during the early stage, interventions target high-centrality hub nodes to suppress outbreak onset; in later stages, resources shift toward peripheral nodes to eliminate residual infections. Contribution/Results: Compared to static centrality-based or uniform allocation baselines, our framework achieves substantial improvements on both synthetic and real-world networks—reducing peak infection by 32.7% on average and cumulative infections by 28.4% on average. It balances global efficiency with fine-grained temporal and structural adaptability, establishing an interpretable, optimization-driven paradigm for time-varying network intervention.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Heuristic Search
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks

Abstract

Rumor propagation in social networks undermines social stability and public trust, calling for interventions that are both effective and resource-efficient. We develop a node-level, time-varying optimal intervention framework that allocates limited resources according to the evolving diffusion state. Unlike static, centrality-based heuristics, our approach derives control weights by solving a resource-constrained optimal control problem tightly coupled to the network structure. Across synthetic and real-world networks, the method consistently lowers both the infection peak and the cumulative infection area relative to uniform and centrality-based static allocations. Moreover, it reveals a stage-aware law: early resources prioritize influential hubs to curb rapid spread, whereas later resources shift to peripheral nodes to eliminate residual transmission. By integrating global efficiency with fine-grained adaptability, the framework offers a scalable and interpretable paradigm for misinformation management and crisis response.

Problem

• Optimizing rumor containment under limited intervention resources
• Developing dynamic node-level control aligned with network structure
• Balancing early hub targeting with late peripheral focus

Innovation

• Node-level time-varying optimal intervention framework
• Resource-constrained control coupled with network structure
• Stage-aware resource allocation shifting from hubs to peripherals