Toward Effective Multimodal Graph Foundation Model: A Divide-and-Conquer Based Approach

Sicheng Liu, Xunkai Li, Daohan Su, Ru Zhang, Hongchao Qin, Rong-Hua Li, Guoren WangICML 2026 · OpenReview

Abstract

Graph Foundation Models (GFMs) have achieved remarkable success in generalizing across diverse domains. However, they mainly focus on Text-Attributed Graphs (TAGs), leaving Multimodal-Attributed Graphs (MAGs) largely untapped. Although recent Multimodal Graph Foundation Models (MGFMs) attempt to bridge this gap by integrating diverse modality information, our empirical investigation reveals two fundamental limitations: (1)they fail to explicitly model modality interaction, essential for capturing intricate cross-modal semantics beyond simple aggregation, and (2)they exhibit sub-optimal modality alignment, which is critical for bridging the significant semantic disparity between distinct modal spaces. To address these challenges, we propose PLANET (graPh topoLogy-aware modAlity iNteraction and alignmEnT), a novel framework employing a Divide-and-Conquer strategy to decouple modality interaction and alignment across distinct granularities. At the embedding granularity, (1)Embedding-wise Domain Gating (EDG) performs local semantic enrichment by adaptively infusing topology-aware cross-modal context, achieving modality interaction. At the node granularity, (2)Node-wise Discretization Retrieval (NDR) ensures global modality alignment by constructing a Discretized Semantic Representation Space (DSRS) to bridge modality gaps. Extensive experiments demonstrate that PLANET significantly outperforms state-of-the-art baselines across diverse graph-centric and multimodal generative tasks. Our code is available at https://github.com/Sapnapnet/PLANET.
BibTeX
@inproceedings{liu2026toward,
  author = {Sicheng Liu and Xunkai Li and Daohan Su and Ru Zhang and Hongchao Qin and Rong-Hua Li and Guoren Wang},
  title = {{Toward Effective Multimodal Graph Foundation Model: A Divide-and-Conquer Based Approach}},
  booktitle = {International Conference on Machine Learning},
  year = {2026},
  url = {https://openreview.net/forum?id=OOodUUenVk},
}

Loading related content...

Figure