mlsanityData to 14 Oct 2026

Modeling Inter-Intra Heterogeneity for Graph Federated Learning

arXiv 2412.11402 ↗First posted 16 Dec 2024cs.LGcited by 12

Not on the map. Why?

Abstract (arXiv)

Heterogeneity is a fundamental and challenging issue in federated learning, especially for the graph data due to the complex relationships among the graph nodes. To deal with the heterogeneity, lots of existing methods perform the weighted federation based on their calculated similarities between pairwise clients (i.e., subgraphs). However, their inter-subgraph similarities estimated with the outputs of local models are less reliable, because the final outputs of local models may not comprehensively represent the real distribution of subgraph data. In addition, they ignore the critical intra-heterogeneity which usually exists within each subgraph itself. To address these issues, we propose a novel Federated learning method by integrally modeling the Inter-Intra Heterogeneity (FedIIH). For the inter-subgraph relationship, we propose a novel hierarchical variational model to infer the whole distribution of subgraph data in a multi-level form, so that we can accurately characterize the inter-subgraph similarities with the global perspective. For the intra-heterogeneity, we disentangle the subgraph into multiple latent factors and partition the model parameters into multiple parts, where each part corresponds to a single latent factor. Our FedIIH not only properly computes the distribution similarities between subgraphs, but also learns disentangled representations that are robust to irrelevant factors within subgraphs, so that it successfully considers the inter- and intra- heterogeneity simultaneously. Extensive experiments on six homophilic and five heterophilic graph datasets in both non-overlapping and overlapping settings demonstrate the effectiveness of our method when compared with nine state-of-the-art methods. Specifically, FedIIH averagely outperforms the second-best method by a large margin of 5.79% on all heterophilic datasets.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 24 of its 40 references that are in the map. First posted on arXiv 16 Dec 2024.

Builds on

24 of 40 references.

References · 24

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2017Inductive Representation Learning on Large Graphscited by 6,320
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  4. 2016Variational Graph Auto-Encoderscited by 1,382
  5. 2020Personalized Federated Learning with Moreau Envelopescited by 618
  6. 2019Federated Learning with Personalization Layerscited by 541
  7. 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 503
  8. 2023A critical look at the evaluation of GNNs under heterophily: Are we really making progress?cited by 343
  9. 2017Advances in Variational Inferencecited by 236
  10. 2021Subgraph Federated Learning with Missing Neighbor Generationcited by 132
  11. 2021Federated Graph Classification over Non-IID Graphscited by 114
  12. 2022Federated Learning with Partial Model Personalizationcited by 114
12 more
  1. 2017Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Datacited by 93
  2. 2022Federated Learning on Non-IID Graphs via Structural Knowledge Sharingcited by 88
  3. 2022Graph Attention Multi-Layer Perceptroncited by 83
  4. 2020Federated Learning via Posterior Averaging: A New Perspective and Practical Algorithmscited by 78
  5. 2022Personalized Federated Learning via Variational Bayesian Inferencecited by 68
  6. 2022Personalized Subgraph Federated Learningcited by 54
  7. 2020Multimodal Generative Learning Utilizing Jensen-Shannon-Divergencecited by 48
  8. 2024FedGTA: Topology-aware Averaging for Federated Graph Learningcited by 44
  9. 2021A Bayesian Federated Learning Framework with Online Laplace Approximationcited by 41
  10. 2024AdaFGL: A New Paradigm for Federated Node Classification with Topology Heterogeneitycited by 25
  11. 2022FedGS: Federated Graph-based Sampling with Arbitrary Client Availabilitycited by 10
  12. 2024FedGT: Federated Node Classification with Scalable Graph Transformercited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 9.

12 papers.

  1. 2026MM-OpenFGL: A Comprehensive Benchmark for Multimodal Federated Graph Learningcited by 11
  2. 2025A Comprehensive Data-centric Overview of Federated Graph Learningcited by 7
  3. 2025Homophily Heterogeneity Matters in Graph Federated Learning: A Spectrum Sharing and Complementing Perspectivecited by 4
  4. 2026PRISM: Topology-Aware Cross-Modal Imputation for Modality-Deficient Federated Graph Learningcited by 3
  5. 2025Federated CLIP for Resource-Efficient Heterogeneous Medical Image Classificationcited by 1
  6. 2026Heterogeneity-Aware Knowledge Sharing for Graph Federated Learningcited by 1
  7. 2026Towards Effective Federated Multimodal Graph Learning via Navigating Multifaceted Heterogeneitycited by 1
  8. 2026SDFed: Bridging Local Global Discrepancy via Subspace Refinement and Divergence Control in Federated Prompt Learningcited by 0
  9. 2026Graph Federated Unlearning for Privacy Preservationcited by 0
  10. 2026Beyond Rigid Alignment: Graph Federated Learning via Dual Manifold Calibrationcited by 0
  11. 2026FedOGL: Combating Catastrophic Forgetting in Federated Open-World Multimodal Graph Learningcited by 0
  12. 2026Towards Adaptive Federated Graph Clustering: A Global Community-aware Contrastive Learning-based Approachcited by 0