TFM4POP is 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 and constructs a comprehensive multi-view cascade benchmark that covers all four information views.
Abstract
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.
The Hierarchical Semantic Interest Evolution Network (HSIEN), a novel generative-discriminative framework that significantly alleviates modality misalignment and enhances CTR prediction performance through feature complementarity, is proposed.
Yi-Fan Cao, Rui Wu, Xiang Wang et al.· Proceedings of the Thirty-Fi...· 0 citations
The basic ideas of online diffusion are introduced by formalising cascade and global graphs, and the extraction of structural and temporal features is described, and the shift toward modelling stochastic cascade dynamics is highlighted.
Hong-Fan Zhu· Theoretical and Natural Scie...· 0 citations
TimePop is a posting-time-aware deep learning framework for short-video popularity prediction that combines multi-granularity temporal attributes of the posting moment into a 14-dimensional continuous vector via sinusoidal-cosinusoidal cyclic encoding, effectively preserving the circular continuity of temporal signals.
Di Wu, Yan-Fei Zhou, Hai-Long Li et al.· Discover Artificial Intellig...· 0 citations
Accurately predicting the popularity of information cascades facilitates the development of social media network applications. During the cascade propagation process, user-generated comments continually evolve, thereby substantially affecting overall information popularity.
However, existing methods primarily focus on...
Yi-Fan Meng, Xi-Gang Sun, An-Ran Zhang et al.· Proceedings of the Thirty-Fi...· 0 citations
A novel Multi-Hop Lightweight Graph Convolutional Network (MH-LGCN) conversational recommendation model based on a multi-hop attention mechanism that abandons redundant operations in traditional graph convolution and designs a lightweight information propagation mechanism that retains only neighbor feature aggregation.
Xua Li, Ru-Jun Wang· International Conference on...· 0 citations
A comprehensive popularity score from likes, comments, favorites, and shares is developed, where principal component analysis determines data-driven indicator weights and the 80th percentile defines a dynamic popularity boundary, suggesting that reliable popularity prediction requires both effective multimodal content...