PRISM: Iterative Cross-Modal Posterior Refinement for Dynamic Text-Attributed Graphs

TL;DR

PRISM introduces an iterative cross-modal refinement framework for dynamic text-attributed graphs, enhancing representation learning by modeling evolving semantic and behavioral dependencies.

Contribution

It proposes organizing DyTAG information into semantic and behavioral modalities and refining their interaction iteratively, improving over rigid fusion strategies.

Findings

PRISM outperforms existing methods on temporal link prediction.

It achieves strong results on destination node retrieval tasks.

Ablation studies confirm the effectiveness of the semantic-behavioral modeling.

Abstract

Dynamic text-attributed graphs (DyTAGs) provide a powerful framework for modeling evolving systems in which node semantics and time-dependent interactions are tightly coupled. Recently, multimodal learning has emerged as a promising yet underexplored direction for enhancing DyTAG representation learning. However, existing methods typically rely on rigid modality partitions and one-shot fusion strategies, which limit their ability to capture the intrinsic and evolving dependencies between node semantics and interaction behaviors. To address these limitations, we propose \textbf{PRISM}, an iterative cross-modal posterior refinement framework for DyTAG representation learning. PRISM organizes DyTAG information into semantic and behavioral modalities, providing a more intrinsic alternative to carrier-level modality partitions. Instead of fusing the two modalities in a single step, PRISM learns a refinement trajectory that progressively transforms semantic priors into behavior-conditioned posterior states through cross-modal interaction with behavioral evidence. Extensive experiments on DTGB benchmark datasets show that PRISM achieves strong performance on temporal link prediction and destination node retrieval tasks. Further ablation studies validate the effectiveness of semantic--behavioral modeling and iterative posterior refinement.