# PACIFIER: Pacing Opinion Depolarization via a Unified Graph Learning Framework

arXiv: https://arxiv.org/abs/2602.23390 · HTML: https://mlsanity.com/paper/2602.23390/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 34 references that are in the map.
- First posted on arXiv 23 Feb 2026.

## Builds on (most cited first, 10 of 10)

- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Learning Combinatorial Optimization Algorithms over Graphs](https://mlsanity.com/paper/1704.01665/) (2017)
- [Deep Graph Representation Learning and Optimization for Influence Maximization](https://mlsanity.com/paper/2305.02200/) (2023)
- [Influence maximization in complex networks through optimal percolation](https://mlsanity.com/paper/1506.08326/) (2015)
- [Minimizing Polarization and Disagreement in Social Networks](https://mlsanity.com/paper/1712.09948/) (2017)
- [Network dismantling](https://mlsanity.com/paper/1603.08883/) (2016)
- [Opinion Optimization in Directed Social Networks](https://mlsanity.com/paper/2306.16847/) (2023)
- [A Nearly-Linear Time Algorithm for Minimizing Risk of Conflict in Social Networks](https://mlsanity.com/paper/2301.05466/) (2023)
- [Minimizing Polarization in Noisy Leader-Follower Opinion Dynamics](https://mlsanity.com/paper/2308.07008/) (2023)
- [Online Minimization of Polarization and Disagreement via Low-Rank Matrix Bandits](https://mlsanity.com/paper/2510.00803/) (2025)

## Abstract (arXiv)

Online social networks often form opposing echo chambers that reinforce opinion polarization. Under the Friedkin-Johnsen (FJ) model, ModerateInternal (MI) and ModerateExpressed (ME) reduce polarization by neutralizing selected users' internal or expressed opinions, but existing solutions are largely model-specific and learning-based depolarization remains underexplored. We study FJ-based moderation as feedback-free autoregressive sequential planning and propose PACIFIER, a unified graph-learning framework that constructs ordered intervention sequences from the initial graph-opinion instance without using recomputed post-intervention expressed opinions as intermediate feedback. PACIFIER combines history-aware node representations with Greedy and RL variants for immediate and long-horizon action scoring, and supports MI, ME, continuous opinions, cost-aware moderation, and node removal. We evaluate intervention trajectories by Accumulated Normalized Polarization (ANP). Trained only on synthetic graphs with fewer than 50 nodes, PACIFIER transfers to 15 real-world Twitter networks with up to 155,599 nodes. It improves over the strongest non-PACIFIER baseline by up to 35.3%, while PACIFIER-RL improves over PACIFIER-Greedy by up to 37.69%. Compared with oracle-style Greedy, PACIFIER retains 98.94% and 97.39% near-oracle quality on MI and ME, respectively, and is about 600x faster at the 450-node range. The source code is available at https://github.com/RickyYY-SZU/PACIFIER