cs.AINov 6, 2026

MM-DyGraph: A Dataset, Benchmark, and Model for Multimodal Dynamic Graphs

Authors: Zongyuan Wu, Pengjie Wang, Lingshan Chen, Tianhang Wan, Yuan Meng, Xin Wang, Ling Feng, Wenwu Zhu

Organizations: DCST, Tsinghua University, Beijing, China · Zhili College, Tsinghua University, Beijing, China

Abstract

Multimodal dynamic graphs are pervasive in real-world applications, where nodes and edges are accompanied by multimodal signals, including text and images. Despite their practical importance, benchmarks and methods that explicitly study multimodal learning in dynamic graphs remain scarce, hindering the full understanding and effective utilization of multimodal information for downstream tasks. To address this gap, we introduce MM-DyGraph, to the best of our knowledge, the first benchmark for multimodal dynamic graph learning, consisting of diverse real-world datasets with fine-grained temporal graph evolution and rich multimodal attributes. MM-DyGraph provides three evaluation tasks to comprehensively assess model performance in dynamic settings. We benchmark representative state-of-the-art dynamic graph methods and reveal that naive feature concatenation yields target-level inconsistencies: multimodal inputs benefit certain prediction targets while harming others. This observation indicates that the modality informativeness depends on the specific prediction target over time. Building on these observations, we propose a Target-aware Spatial-Temporal Multimodal Fusion (TST-MF) framework, which jointly conditions multimodal fusion on the prediction target and spatial-temporal relations, enabling context-adaptive cross-modal interplay for target-specific representations. Extensive experiments over diverse datasets and tasks show that TST-MF delivers robust and competitive performance, achieving clear gains in multimodal settings.

Figures & tables

Appendix figures & tables27 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Multimodal Graph Representation Learning with Dynamic Information Pathways

    Mar 10, 2026Xiaobin Hong, Mingkai Lin, Xiaoli Wang +2Multimodal Graph LearningMultimodal Embedding

  2. DyMRL: Dynamic Multispace Representation Learning for Multimodal Event Forecasting in Knowledge Graph

    Mar 25, 2026Feng Zhao, Kangzheng Liu, Teng Peng +2Multimodal KGsTemporal KGs

  3. TMTE: Effective Multimodal Graph Learning with Task-aware Modality and Topology Co-evolution

    Mar 29, 2026Yinlin Zhu, Xunkai Li, Di Wu +3Multimodal Graph LearningGraph Structure Learning