FedLAB: 面向联邦多模态图基础学习的可追踪语义码本
FedLAB: Traceable Semantic Codebooks for Federated Multimodal Graph Foundation Learning
AI总结：
提出FedLAB框架，通过类型化分层码本组织模态证据、节点语义和拓扑上下文，实现联邦多模态图学习中的可追踪语义，在10个基准和6个下游任务上提升达7.53%。
摘要：
多模态图基础模型旨在从富含文本、图像、属性和关系拓扑的图中学习可重用知识，从而支持多样化的以图为中心和以模态为中心的任务。然而，在实践中，此类多模态图通常分布在去中心化的客户端上，由于隐私约束，原始内容和局部结构无法集中共享。这推动了联邦多模态图基础学习，它不仅需要可迁移的表示学习，还需要在严格数据隔离下实现内在的语义可追踪性。现有方法通常通过参数、原型、嵌入或紧凑码本交换或存储知识，这些方法支持优化和迁移，但并未明确揭示模态证据、节点语义和拓扑上下文如何共同支持预测。为弥补这一差距，我们提出了FedLAB，一个可追踪的语义码本框架，它将多模态图知识组织为用于模态证据、节点语义和拓扑上下文的类型化分层码本。FedLAB通过联邦语义重心预训练进一步细化这些追踪单元，同时保持原始多模态内容和图结构的本地性。在10个基准和6个下游任务上的大量实验表明，FedLAB相比最先进的基线提升了高达7.53%，同时保留了原生的语义追踪接口。
英文摘要：
Multimodal graph foundation models aim to learn reusable knowledge from graphs enriched with text, images, attributes, and relational topology, thereby supporting diverse graph-centric and modality-centric tasks. In practice, however, such multimodal graphs are often distributed across decentralized clients, where raw contents and local structures cannot be centrally shared due to privacy constraints. This motivates federated multimodal graph foundation learning, which requires not only transferable representation learning but also intrinsic semantic traceability under strict data isolation. Existing methods usually exchange or store knowledge through parameters, prototypes, embeddings, or compact codebooks, which support optimization and transfer but do not explicitly expose how modality evidence, node semantics, and topology context jointly support predictions. To bridge this gap, we propose FedLAB, a traceable semantic codebook framework that organizes multimodal graph knowledge into typed hierarchical codebooks for modality evidence, node semantics, and topology context. FedLAB further refines these trace units through federated semantic barycenter pre-training while keeping raw multimodal contents and graph structures local. Extensive experiments on 10 benchmarks and 6 downstream tasks show that FedLAB improves over state-of-the-art baselines by up to 7.53\%, while preserving a native semantic trace interface.
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。
