Research map / Graph learning / GNN architectures

Normalized Friedkin–Johnsen Opinion Dynamics

NeurIPS 2026 · Graph learning › GNN architectures · approach: Physics-inspired GNNs

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a normalized variant of the Friedkin–Johnsen opinion dynamics model for opinion aggregation on social platforms. Only the abstract was available, so details are limited.

Problem

Opinion dynamics models such as the Friedkin–Johnsen (FJ) model are widely studied for predicting how opinions propagate on online social platforms, but the abstract provided gives no further detail on the specific shortcoming addressed.

Approach

Introduces a normalized version of the Friedkin–Johnsen model; the abstract does not state the specific normalization or how it differs from prior FJ formulations.

Limitations

• Full text unavailable; only the abstract was used

Experimental setup

Builds on: Friedkin-Johnsen model

Closest papers by meaning

• Fast Computation and Optimization for Opinion-Based Quantities of Friedkin-Johnsen Model (NeurIPS 2025 · similarity 0.87)
• Sample Complexity of Linear Regression Models for Opinion Formation in Networks (AAAI 2025 · similarity 0.85)
• Opinion Maximization in Social Networks by Modifying Internal Opinions (NeurIPS 2025 · similarity 0.84)
• Optimizing Social Network Interventions via Hypergradient-Based Recommender System Design (ICML 2025 · similarity 0.83)
• Reaching a Consensus in Predictive Loops (NeurIPS 2026 · similarity 0.82)
• Expressive and Flexible Simulation of Information Spread Strategies in Social Networks Using Planning (AAAI 2024 · similarity 0.82)