用统一图学习框架动态干预社交网络，缓解观点极化。
PACIFIER: Pacing Opinion Depolarization via a Unified Graph Learning Framework
- 将极化调控建模为无反馈的序列规划，通过历史感知节点表征生成干预顺序。
- 在15个真实微博网络上提升去极化效果最高达35.3%，比基线快600倍。
- 支持多种调控策略，且仅在小规模合成数据上训练即可跨域适用。
在线社交网络常形成对立回音室，加剧观点极化。基于Friedkin-Johnsen（FJ）模型的中立内化（MI）和中立外显（ME）可通过调节部分用户的内在或外在意见来缓解极化，但现有方法多依赖特定模型，基于学习的去极化仍缺乏探索。本文将FJ驱动的调节视为无反馈的自回归序列规划，提出PACIFIER——一种统一的图学习框架，从初始图-观点实例构建有序干预序列，无需使用干预后重计算的表达观点作为中间反馈。PACIFIER结合历史感知节点表示与贪婪及强化学习变体，实现即时与长期动作评分，支持MI、ME、连续观点、成本敏感调节及节点移除。采用累积归一化极化（ANP）评估干预轨迹。仅在少于50个节点的合成图上训练，PACIFIER可迁移至15个真实世界微博网络（最大155,599节点），性能优于最强非PACIFIER基线最高达35.3%；其中PACIFIER-RL相比PACIFIER-Greedy提升高达37.69%。相较理想贪婪策略，PACIFIER在MI和ME场景下分别保持近似98.94%和97.39%的接近最优表现，且在450节点规模下速度提升约600倍。源代码已公开于https://github.com/RickyYY-SZU/PACIFIER。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。