mlsanityData to 13 Oct 2026

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

arXiv 2601.22416 ↗First posted 29 Jan 2026cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 11 papers in the map (data through 13 Oct 2026). Builds on 61 of its 74 references that are in the map. First posted on arXiv 29 Jan 2026.

Builds on

61 of 74 references.

References · 61

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,318
  2. 2017Graph Attention Networkscited by 8,888
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,653
  4. 2017Inductive Representation Learning on Large Graphscited by 6,303
  5. 2018How Powerful are Graph Neural Networks?cited by 4,373
  6. 2018Federated Optimization in Heterogeneous Networkscited by 2,981
  7. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,086
  8. 2015Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Modelscited by 1,355
  9. 2021Model-Contrastive Federated Learningcited by 766
  10. 2020Think Locally, Act Globally: Federated Learning with Local and Global Representationscited by 324
  11. 2023One for All: Towards Training One Graph Model for All Classification Taskscited by 240
  12. 2021FedKD: Communication Efficient Federated Learning via Knowledge Distillationcited by 187
38 more
  1. 2022FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correctioncited by 181
  2. 2021RedCaps: web-curated image-text data created by the people, for the peoplecited by 178
  3. 2021Training Graph Neural Networks with 1000 Layerscited by 169
  4. 2021Subgraph Federated Learning with Missing Neighbor Generationcited by 132
  5. 2023GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learnercited by 131
  6. 2021Federated Graph Classification over Non-IID Graphscited by 114
  7. 2023Stochastic Controlled Averaging for Federated Learning with Communication Compressioncited by 100
  8. 2020Graph Structured Network for Image-Text Matchingcited by 93
  9. 2022Federated Learning on Non-IID Graphs via Structural Knowledge Sharingcited by 88
  10. 2024GFT: Graph Foundation Model with Transferable Tree Vocabularycited by 83
  11. 2020Federated Mutual Learningcited by 71
  12. 2023FedExP: Speeding Up Federated Averaging via Extrapolationcited by 69
  13. 2024GraphCLIP: Enhancing Transferability in Graph Foundation Models for Text-Attributed Graphscited by 58
  14. 2024AnyGraph: Graph Foundation Model in the Wildcited by 52
  15. 2025UniGraph2: Learning a Unified Embedding Space to Bind Multimodal Graphscited by 49
  16. 2024FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learningcited by 47
  17. 2024Mosaic of Modalities: A Comprehensive Benchmark for Multimodal Graph Learningcited by 29
  18. 2024Federated LoRA with Sparse Communicationcited by 26
  19. 2024RAGraph: A General Retrieval-Augmented Graph Learning Frameworkcited by 24
  20. 2024FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extractioncited by 21
  21. 2023NineRec: A Benchmark Dataset Suite for Evaluating Transferable Recommendationcited by 20
  22. 2024Learning Graph Quantized Tokenizerscited by 19
  23. 2020The multilayer random dot product graphcited by 18
  24. 2023An Image Dataset for Benchmarking Recommender Systems with Raw Pixelscited by 17
  25. 2024FedMM: Federated Multi-Modal Learning with Modality Heterogeneity in Computational Pathologycited by 17
  26. 2024OpenFGL: A Comprehensive Benchmark for Federated Graph Learningcited by 16
  27. 2024FedMAC: Tackling Partial-Modality Missing in Federated Learning with Cross-Modal Aggregation and Contrastive Regularizationcited by 16
  28. 2024FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preferencecited by 16
  29. 2024Deep Efficient Private Neighbor Generation for Subgraph Federated Learningcited by 14
  30. 2024MH-pFLID: Model Heterogeneous personalized Federated Learning via Injection and Distillation for Medical Data Analysiscited by 14
  31. 2024Leveraging Foundation Models for Multi-modal Federated Learning with Incomplete Modalitycited by 14
  32. 2024Recurrent Early Exits for Federated Learning with Heterogeneous Clientscited by 12
  33. 2024Modeling Inter-Intra Heterogeneity for Graph Federated Learningcited by 12
  34. 2024Federated Graph Condensation with Information Bottleneck Principlescited by 8
  35. 2025Learning Reconfigurable Representations for Multimodal Federated Learning with Missing Datacited by 8
  36. 2021Multiplex Graph Networks for Multimodal Brain Network Analysiscited by 7
  37. 2025Towards A Universal Graph Structural Encodercited by 7
  38. 2025S2FGL: Spatial Spectral Federated Graph Learningcited by 7

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2026: 11.

11 papers.

  1. 2026STAGE: Tackling Semantic Drift in Multimodal Federated Graph Learningcited by 3
  2. 2026PRISM: Topology-Aware Cross-Modal Imputation for Modality-Deficient Federated Graph Learningcited by 3
  3. 2026GRM: Utility-Aware Jailbreak Attacks on Audio LLMs via Gradient-Ratio Maskingcited by 1
  4. 2026Towards Robust Federated Multimodal Graph Learning under Modality Heterogeneitycited by 1
  5. 2026FedLAB: Traceable Semantic Codebooks for Federated Multimodal Graph Foundation Learningcited by 1
  6. 2026Toward Federated Multimodal Graph Foundation Models: A Topology-Aware Multimodal Alignment Frameworkcited by 1
  7. 2026Towards Effective Federated Multimodal Graph Learning via Navigating Multifaceted Heterogeneitycited by 1
  8. 2026Towards Modality-imbalanced Federated Graph Learning: A Data Synthesis-based Approachcited by 0
  9. 2026FedOGL: Combating Catastrophic Forgetting in Federated Open-World Multimodal Graph Learningcited by 0
  10. 2026MMFGU: Multimodal Federated Graph Unlearningcited by 0
  11. 2026Coupling Perception and Reasoning in Federated Multimodal Graph Foundation Modelscited by 0