提出动态路径机制，让多模态图神经网络更灵活高效地融合图文信息。
Multimodal Graph Representation Learning with Dynamic Information Pathways
- 用伪节点实现模态内动态消息路由，按相似性自动选择传播路径
- 在多个基准上超越基线，链接预测和节点分类准确率均有提升
- 适合处理图像与文本混合的复杂图数据，如社交网络、知识图谱
多模态图中节点包含图像、文本等异构特征，在真实场景中日益普遍。有效学习此类图需兼顾模态内自适应消息传递与模态间高效聚合。然而，现有方法多基于传统图神经网络扩展，依赖静态结构或稠密注意力，限制了灵活性与嵌入表达能力。本文提出一种新型多模态图表示学习框架——动态信息路径（DiP）。通过引入模态特定伪节点，DiP 利用邻近性引导的伪节点交互实现模态内动态消息路由，并在共享状态空间中通过高效信息路径捕捉模态间依赖关系。该设计实现了跨模态自适应、高表达力且稀疏的消息传播，计算复杂度为线性。我们在链接预测与节点分类任务上评估性能，并进行完整实验分析。在多个基准上的大量实验表明，DiP 持续优于基线方法。
原文摘要 · Abstract (English)
Multimodal graphs, where nodes contain heterogeneous features such as images and text, are increasingly common in real-world applications. Effectively learning on such graphs requires both adaptive intra-modal message passing and efficient inter-modal aggregation. However, most existing approaches to multimodal graph learning are typically extended from conventional graph neural networks and rely on static structures or dense attention, which limit flexibility and expressive node embedding learning. In this paper, we propose a novel multimodal graph representation learning framework with Dynamic information Pathways (DiP). By introducing modality-specific pseudo nodes, DiP enables dynamic message routing within each modality via proximity-guided pseudo-node interactions and captures inter-modality dependence through efficient information pathways in a shared state space. This design achieves adaptive, expressive, and sparse message propagation across modalities with linear complexity. We conduct the link prediction and node classification tasks to evaluate performance and carry out full experimental analyses. Extensive experiments across multiple benchmarks demonstrate that DiP consistently outperforms baselines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。