arXiv：cs.LG· Xunkai Li, Chenxi Wan, Yinlin Zhu, Wang Luo, Hongchao Qin, Rong-Hua Li, Guoren Wang·· 5 小时前AI 评分30
GraphBind：一种拓扑驱动的全能多模态图基础模型方法
Toward Omni Multimodal Graph Foundation Model: A Topology-Driven Binding Approach
AI 导读
GraphBind 是一种拓扑驱动的多模态图基础模型方法，利用图拓扑的稳定性将多模态信息绑定到统一共享空间，以应对多模态属性图中节点属性不完整的问题。在针对 11 个代表性基线的实验中，GraphBind 在判别和生成任务上均取得领先性能，相对最强基线提升最高达 28.1%。
正文
Abstract:Multimodal graph foundation models (MGFMs) seek to learn generalizable representations from large-scale graphs with heterogeneous node modalities. However, real-world Multimodal-Attributed Graphs (MAGs) often contain incomplete node attributes, limiting the scale and diversity of available pretraining corpora. Besides, existing MGFMs primarily incorporate graph topology as structural context, overlooking its role in guiding multimodal binding and shaping a unified representation space. To address these challenges, we propose GraphBind, a topology-driven approach that uses graph topology to bind rich modality information into a unified shared space. GraphBind is motivated by the stability of graph topology, which provides structural references and complementary semantic information for multimodal binding. Concretely, GraphBind uses topology to organize self semantics and reliable neighborhood semantics into a global shared space that integrates structure and semantics, and adapts this space to discriminative and generative tasks through lightweight interfaces. Extensive experiments against 11 representative baselines demonstrate that GraphBind achieves leading performance on both discriminative and generative tasks, with relative improvements of up to 28.1% over the strongest baseline.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.02881 [cs.LG] |
| (or arXiv:2610.02881v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02881 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xunkai Li [view email]
[v1]
Fri, 2 Oct 2026 06:18:18 UTC (1,055 KB)
来源：arXiv：cs.LG · arxiv.org