PACIFIER: Pacing Opinion Depolarization via a Unified Graph Learning Framework

[2602.23390] PACIFIER: Pacing Opinion Depolarization via a Unified Graph Learning Framework Skip to main content Search Submit Donate Log in Computer Science > Social and Information Networks arXiv:2602.23390 (cs) [Submitted on 23 Feb 2026 ( v1 ), last revised 27 Aug 2026 (this version, v4)] Title: PACIFIER: Pacing Opinion Depolarization via a Unified Graph Learning Framework Authors: Mingkai Liao , Zijun Zhang , Mingyang Zhou View PDF HTML (experimental) Abstract: 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 this https URL Comments: 11 pages. Accepted at the 35th ACM International Conference on Information and Knowledge Management (CIKM 2026) Subjects: Social and Information Networks (cs.SI) ; Machine Learning (cs.LG) Cite as: arXiv:2602.23390 [cs.SI] (or arXiv:2602.23390v4 [cs.SI] for this version) https://doi.org/10.48550/arXiv.2602.23390 Focus to learn more arXiv-issued DOI via DataCite Related DOI : https://doi.org/10.1145/3799682.3840684 Focus to learn more DOI(s) linking to related resources Submission history From: Mingkai Liao [ view email ] [v1] Mon, 23 Feb 2026 11:57:04 UTC (14,899 KB) [v2] Sun, 12 Apr 2026 07:41:44 UTC (17,194 KB) [v3] Wed, 29 Apr 2026 10:07:40 UTC (25,777 KB) [v4] Thu, 27 Aug 2026 08:30:49 UTC (1,232 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.SI < prev | next > new | recent | 2026-02 Change to browse by: cs cs.LG References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• PACIFIER: Pacing Opinion Depolarization via a Unified Graph Learning Framework#677508
• ProxyMOS: Label-Free Speech Quality Assessment by Multi-Teacher Distillation with Adaptive Routing#1155354
• Let Prompts Bridge Defense Knowledge: Transferable Graph Purification via Vulnerability-Aware GPL#793277
• Let Prompts Bridge Defense Knowledge: Transferable Graph Purification via Vulnerability-Aware GPL#789273
• Correcting What You Cannot See: Credit Assignment for Perception Distillation in Multimodal Reasoners#414157