Work

Neural Network-based Stability Guarantee for Dissensus Opinion Behaviors on the Sphere

Year: 2025

Type: article

Abstract: In this paper, we develop a neural network-based method to study opinion behaviors under a covariance-based dissensus algorithm. Driven by this dissensus algorithm, the opinions are updated based on relative interactions and gradually converge to dissensus on the sphere. This proposed neural network-based method samples data and trains a neural network to ensure the Lyapunov conditions, which significantly simplifies the Lyapunov function design for stability analysis. The regions of attraction for different dissensus equilibria can also be estimated under opinion dynamics on a unit sphere by training a neural network to approximate the solution of Zubov’s equation. Simulations demonstrate the performance of the proposed method.

Source: IFAC-PapersOnLine

DOI: 10.1016/j.ifacol.2025.07.044

Authors: Junkai Wang, Ziqiao Zhang, Fumin Zhang

Institutions: Georgia Institute of Technology, Purdue University West Lafayette, Hong Kong University of Science and Technology

Language: English

Topic: Opinion Dynamics and Social Influence

Subfield: Statistical and Nonlinear Physics

Field: Physics and Astronomy

Domain: Physical Sciences

Open Access status: diamond

Funders: National Science Foundation, National Oceanic and Atmospheric Administration, Office of Naval Research, Air Force Office of Scientific Research