点击次数：

发表刊物：Information Sciences

摘要：Large-scale group decision making needs consensus rules that are robust to uncertainty yet easy to interpret. We propose TWD-SCD, a consensus framework built on three-way decision. At each step every decision maker is placed in a positive, boundary, or negative region based on its distance from the group, and each region triggers a different update: keep the opinion, mix it mildly with the group mean, or average it over the social network. A lightweight Q-learning policy tunes the region thresholds online. We analyze the fixed-threshold kernel and the learning policy separately. For the fixed-threshold kernel, we give concrete, checkable conditions on the network and the thresholds under which a contraction holds, yielding almost-sure consensus when noise decays and a bounded error floor when noise is constant. A mean-field argument predicts a critical threshold, and a residual test bounds how well cooperative and non-cooperative decision makers can be told apart before consensus erases the evidence. We evaluate TWD-SCD against eight baselines on random graphs (up to �� =3000), with further tests on the real email-Eu-core topology and on MovieLens ratings. It matches DeGroot’s consensus level at lower adjustment cost and lower variance under non-cooperative behavior.

论文类型：期刊论文

论文编号：12054

卷号：759

是否译文：否

发表时间：2026-09-29

收录刊物：SCI

第一作者：Bo Sun

合写作者：Chunmao Jiang,Ruyi Ye,Hao Zhang