MM-OpenFGL: A Comprehensive Benchmark for Multimodal Federated Graph Learning

2026-01-29

AI Summary

This work addresses the challenge that multimodal graph data are often inaccessible due to privacy and commercial constraints, while existing federated graph learning approaches fail to effectively tackle the unique difficulties of multimodal federated graph learning (MMFGL). To bridge this gap, the paper presents the first systematic formulation of the MMFGL paradigm and introduces MM-OpenFGL, the first comprehensive benchmark for this setting. MM-OpenFGL encompasses 19 datasets, 8 simulation strategies, 6 tasks, and 57 methods, offering a modular API that uniformly supports key components including multimodal modeling, federated protocols, heterogeneous alignment, and topology simulation. Extensive experiments validate the framework’s necessity, effectiveness, robustness, and efficiency, thereby establishing a foundational resource that fills a critical void in systematic MMFGL research and paves the way for future advancements.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing

Abstract

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.

Problem

• Multimodal Federated Graph Learning
• MMAGs
• Federated Graph Learning
• Privacy-Preserving Learning
• Distributed Graph Data

Innovation

• Multimodal Federated Graph Learning
• Benchmark
• Federated Learning
• Graph Neural Networks
• Privacy-Preserving AI