每一点帮助都有价值：通过细粒度可迁移多模态标记构建知识图谱基础模型
Every Little Helps: Building Knowledge Graph Foundation Model with Fine-grained Transferable Multi-modal Tokens
AI总结：
本文提出TOFU模型，通过细粒度可迁移多模态标记提升多模态知识图谱推理的跨图谱迁移能力。
摘要：
多模态知识图谱推理（MMKGR）旨在通过利用图结构信息和多模态实体内容来预测缺失的链接。大多数现有工作都是为传递性设置设计的，它们学习数据集特定的嵌入，并且难以泛化到新的知识图谱。最近的知识图谱基础模型（KGFMs）提高了跨知识图谱的迁移能力，但它们主要利用结构模式，而忽略了丰富的多模态信号。我们通过提出一个基于标记的基础模型（TOFU）来解决这些差距，该模型在不同多模态知识图谱中表现出强大的泛化能力。TOFU将结构、视觉和文本信息离散化为模态特定的标记。TOFU随后采用分层融合架构与混合信息机制，旨在处理这些标记并获得可用于MMKGR的可迁移特征。在17个传递性、诱导性和完全诱导性MMKGs上的实验结果表明，TOFU在不同MMKGs上持续优于强大的KGFM和MMKGR基线，展现出在未见过的MMKGs上的强大性能。
英文摘要：
Multi-modal knowledge graph reasoning (MMKGR) aims to predict the missing links by exploiting both graph structure information and multi-modal entity contents. Most existing works are designed for a transductive setting, which learns dataset-specific embeddings and struggles to generalize to new KGs. Recent knowledge graph foundation models (KGFMs) improve cross-KG transfer, but they mainly exploit structural patterns and ignore rich multi-modal signals. We address these gaps by proposing a token-based foundation model (TOFU) for MMKGR, which exhibits strong generalization across different MMKGs. TOFU discretizes structural, visual, and textual information into modality-specific tokens. TOFU then employs a hierarchical fusion architecture with mixture-of-message mechanisms, aiming to process these tokens and obtain transferable features for MMKGR. Experimental results on 17 transductive, inductive, and fully-inductive MMKGs show that TOFU generally outperforms strong KGFM and MMKGR baselines, delivering strong performance on unseen MMKGs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
