首个多模态联邦图学习基准，解决跨平台协作中的隐私与数据异构问题。
MM-OpenFGL: A Comprehensive Benchmark for Multimodal Federated Graph Learning
- 构建首个系统化多模态联邦图学习评估框架
- 覆盖19个数据集、8种模拟策略、57种方法的全面实验
- 适合研究联邦学习、图神经网络及多模态数据融合的学者
多模态属性图（MMAGs）通过整合异构模态与图结构，为建模复杂关系数据提供统一框架。尽管集中式学习表现良好，但现实中MMAGs常分散于孤立平台，因隐私或商业限制无法共享。联邦图学习（FGL）为此提供了自然解决方案；然而现有研究多聚焦单模态图，未能充分应对多模态联邦图学习（MMFGL）的独特挑战。为此，我们提出MM-OpenFGL，首个系统化形式化MMFGL范式的综合性基准，支持严谨评估。该基准包含19个多模态数据集（涵盖7个应用领域）、8种模拟策略（捕捉模态与拓扑变化）、6项下游任务，以及通过模块化API实现的57种先进方法。大规模实验从必要性、有效性、鲁棒性和效率角度深入探究了MMFGL，为未来研究提供重要洞见。
原文摘要 · Abstract (English)
Multimodal-attributed graphs (MMAGs) provide a unified framework for modeling complex relational data by integrating heterogeneous modalities with graph structures. While centralized learning has shown promising performance, MMAGs in real-world applications are often distributed across isolated platforms and cannot be shared due to privacy concerns or commercial constraints. Federated graph learning (FGL) offers a natural solution for collaborative training under such settings; however, existing studies largely focus on single-modality graphs and do not adequately address the challenges unique to multimodal federated graph learning (MMFGL). To bridge this gap, we present MM-OpenFGL, the first comprehensive benchmark that systematically formalizes the MMFGL paradigm and enables rigorous evaluation. MM-OpenFGL comprises 19 multimodal datasets spanning 7 application domains, 8 simulation strategies capturing modality and topology variations, 6 downstream tasks, and 57 state-of-the-art methods implemented through a modular API. Extensive experiments investigate MMFGL from the perspectives of necessity, effectiveness, robustness, and efficiency, offering valuable insights for future research on MMFGL.
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。