用分层图网络分析谣言传播,提升预测精度。
Enhancing Temporal Link Prediction with HierTKG: A Hierarchical Temporal Knowledge Graph Framework
- 融合时序图网络与分层池化,捕捉谣言传播多尺度特征。
- 在ICEWS14数据集上达到0.9845的MRR,表现领先。
- 适合关注社交媒体谣言预警与干预的研究者。
社交媒体中虚假信息的快速传播,尤其在危机时期,严重干扰公众决策。为应对这一挑战,我们提出HierTKG框架,结合时序图网络(TGN)与分层池化(DiffPool),从时空和结构双重维度建模谣言传播动态。该框架能有效识别关键传播阶段,提升时序链接预测性能,并提供可操作的洞察以控制虚假信息扩散。实验表明,其在ICEWS14数据集上取得0.9845的MRR,在WikiData上达0.9312,且在噪声较大的PHEME数据集上也表现稳健(MRR: 0.8802)。通过建模结构化事件序列与动态社交互动,HierTKG可适应多种传播模式,为实时分析与预测谣言传播提供可扩展、鲁棒的解决方案,支持主动干预策略制定。
原文摘要 · Abstract (English)
The rapid spread of misinformation on social media, especially during crises, challenges public decision-making. To address this, we propose HierTKG, a framework combining Temporal Graph Networks (TGN) and hierarchical pooling (DiffPool) to model rumor dynamics across temporal and structural scales. HierTKG captures key propagation phases, enabling improved temporal link prediction and actionable insights for misinformation control. Experiments demonstrate its effectiveness, achieving an MRR of 0.9845 on ICEWS14 and 0.9312 on WikiData, with competitive performance on noisy datasets like PHEME (MRR: 0.8802). By modeling structured event sequences and dynamic social interactions, HierTKG adapts to diverse propagation patterns, offering a scalable and robust solution for real-time analysis and prediction of rumor spread, aiding proactive intervention strategies.
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。