mlsanityData to 14 Oct 2026

Towards Modality-imbalanced Federated Graph Learning: A Data Synthesis-based Approach

arXiv 2606.20382 ↗First posted 18 Jun 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

MultiModal Federated Graph Learning (MM-FGL) offers a natural collaborative training paradigm, but its practical deployment is challenged by two granularities of modality imbalance. Client-level imbalance occurs when certain clients lack entire modalities, while node-level imbalance occurs when individual nodes exhibit missing visual or textual attributes. While several relevant studies exist, our investigation reveals that they predominantly target graph-agnostic or centralized scenarios, rendering them difficult to adapt directly. To address these challenges, we formalize modality-imbalanced MM-FGL as an implicit graph-aware latent semantic representation synthesis problem. This paradigm recovers missing modal semantics directly within the representation space, thereby maximizing alignment with the original data's semantic distribution and mitigating the high variance induced by missing modalities. To this end, we propose FedMGS (Federated Modality-aware Graph Synthesis), which integrates three core components. The availability-aware graph encoder prevents missing modalities from contaminating local structural propagation. The prototype-guided latent semantic synthesizer establishes cross-client semantic anchors for unavailable modalities. The reliability-calibrated semantic fusion mechanism regulates the impact of recovered latent representations prior to predictive readout. Extensive experiments on four tasks show that FedMGS consistently outperforms competitive baselines with gains up to 17.41% with best efficiency-performance tradeoff.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 28 of its 47 references that are in the map. First posted on arXiv 18 Jun 2026.

Builds on

28 of 47 references.

References · 28

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  4. 2017Inductive Representation Learning on Large Graphscited by 6,320
  5. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  6. 2015Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Modelscited by 1,362
  7. 2018Link Prediction Based on Graph Neural Networkscited by 832
  8. 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 352
  9. 2021Subgraph Federated Learning with Missing Neighbor Generationcited by 132
  10. 2021Federated Graph Classification over Non-IID Graphscited by 114
  11. 2022Federated Learning on Non-IID Graphs via Structural Knowledge Sharingcited by 88
  12. 2023FedMultimodal: A Benchmark For Multimodal Federated Learningcited by 51
16 more
  1. 2025UniGraph2: Learning a Unified Embedding Space to Bind Multimodal Graphscited by 49
  2. 2020Graph Neural Networks: Taxonomy, Advances and Trendscited by 48
  3. 2024FedGTA: Topology-aware Averaging for Federated Graph Learningcited by 44
  4. 2022FederatedScope-GNN: Towards a Unified, Comprehensive and Efficient Package for Federated Graph Learningcited by 43
  5. 2021FedGL: Federated Graph Learning Framework with Global Self-Supervisioncited by 34
  6. 2024Mosaic of Modalities: A Comprehensive Benchmark for Multimodal Graph Learningcited by 29
  7. 2024AdaFGL: A New Paradigm for Federated Node Classification with Topology Heterogeneitycited by 25
  8. 2024Cross-Modal Prototype based Multimodal Federated Learning under Severely Missing Modalitycited by 21
  9. 2024FedMM: Federated Multi-Modal Learning with Modality Heterogeneity in Computational Pathologycited by 17
  10. 2024FedMAC: Tackling Partial-Modality Missing in Federated Learning with Cross-Modal Aggregation and Contrastive Regularizationcited by 16
  11. 2024Leveraging Foundation Models for Multi-modal Federated Learning with Incomplete Modalitycited by 14
  12. 2026MM-OpenFGL: A Comprehensive Benchmark for Multimodal Federated Graph Learningcited by 11
  13. 2024Async Learned User Embeddings for Ads Delivery Optimizationcited by 7
  14. 2025Subgraph Federated Learning via Spectral Methodscited by 6
  15. 20232SFGL: A Simple And Robust Protocol For Graph-Based Fraud Detectioncited by 3
  16. 2026STAGE: Tackling Semantic Drift in Multimodal Federated Graph Learningcited by 3

Built on by

Not cited yet.