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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Xunkai, Ai, Yuming, Zhu, Yinlin, Lu, Haodong, Zhang, Yi, Fu, Guohao, Fan, Bowen, Dai, Qiangqiang, Li, Rong-Hua, Wang, Guoren
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908799057526784
author Li, Xunkai
Ai, Yuming
Zhu, Yinlin
Lu, Haodong
Zhang, Yi
Fu, Guohao
Fan, Bowen
Dai, Qiangqiang
Li, Rong-Hua
Wang, Guoren
author_facet Li, Xunkai
Ai, Yuming
Zhu, Yinlin
Lu, Haodong
Zhang, Yi
Fu, Guohao
Fan, Bowen
Dai, Qiangqiang
Li, Rong-Hua
Wang, Guoren
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_22416
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MM-OpenFGL: A Comprehensive Benchmark for Multimodal Federated Graph Learning
Li, Xunkai
Ai, Yuming
Zhu, Yinlin
Lu, Haodong
Zhang, Yi
Fu, Guohao
Fan, Bowen
Dai, Qiangqiang
Li, Rong-Hua
Wang, Guoren
Machine Learning
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.
title MM-OpenFGL: A Comprehensive Benchmark for Multimodal Federated Graph Learning
topic Machine Learning
url https://arxiv.org/abs/2601.22416