面向多视图信息级联流行度预测的表格基础模型
Tabular Foundation Models for Multi-View Information Cascade Popularity Prediction
浏览论文内容
中文总结 AI 辅助
该研究针对信息级联流行度预测的现有局限，提出双分支设计的TFM4POP框架，结合表格基础模型与神经ODE编码器，通过参数高效微调实现多视图建模，在多数据集上优于现有方法。
中文摘要 AI 辅助
预测信息级联的未来流行度对于理解社交媒体上的信息传播至关重要。尽管近期取得了进展，现有方法仍面临两个关键局限：它们主要关注级联视图，而忽略了推动用户参与的其他信息视图，如文本语义、视觉内容和表格属性；且无法捕捉高阶跨视图交互。为解决这些问题，我们提出TFM4POP，首个将表格基础模型（TFMs）引入流行度预测的框架，利用其预训练表格先验统一建模多种异构信息视图。具体而言，TFM4POP采用双分支设计：静态分支以TFM为特征编码骨干，通过上下文学习联合推理所有静态视图，生成静态级联表示；动态分支采用专用的基于神经ODE的编码器捕捉连续时间的级联动态。两种表示通过交叉注意力融合以完成最终预测。此外，为使TFM适配真实级联分布，我们采用参数高效的IA3微调，在更新参数少得多的情况下，实现与全量微调相当或更优的性能。我们还构建了涵盖全部四个信息视图的综合多视图级联基准。大量实验表明，TFM4POP在多个数据集和观测设置下，始终优于最先进的基线方法。
英文摘要
Predicting the future popularity of information cascades is essential for understanding information diffusion on social media. Despite recent advances, existing methods face two key limitations: they focus primarily on the cascade view while overlooking other information views that drive user engagement, such as textual semantics, visual content, and tabular attributes; and they fail to capture high-order cross-view interactions. To address these issues, we propose \textbf{TFM4POP}, the first framework to introduce tabular foundation models (TFMs) into popularity prediction, leveraging their pre-trained tabular priors to unify the modeling of multiple heterogeneous information views. Specifically, TFM4POP adopts a dual-branch design: the static branch employs a TFM as the feature-encoding backbone that jointly reasons over all static views through in-context learning to produce the static cascade representation, while the dynamic branch captures the continuous-time cascade dynamics with a dedicated Neural-ODE-based encoder. The two representations are then fused via cross-attention for the final prediction. Furthermore, to adapt the TFM to real cascade distributions, we apply parameter-efficient IA3 fine-tuning, achieving performance competitive with or better than full fine-tuning while updating substantially fewer parameters. In addition, we construct a comprehensive multi-view cascade benchmark that covers all four information views. Extensive experiments show that TFM4POP consistently outperforms state-of-the-art baselines across multiple datasets and observation settings.
