mlsanityData to 14 Oct 2026

Homophily Heterogeneity Matters in Graph Federated Learning: A Spectrum Sharing and Complementing Perspective

arXiv 2502.13732 ↗First posted 19 Feb 2025cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Since heterogeneity presents a fundamental challenge in graph federated learning, many existing methods are proposed to deal with node feature heterogeneity and structure heterogeneity. However, they overlook the critical homophily heterogeneity, which refers to the substantial variation in homophily levels across graph data from different clients. The homophily level represents the proportion of edges connecting nodes that belong to the same class. Due to adapting to their local homophily, local models capture inconsistent spectral properties across different clients, significantly reducing the effectiveness of collaboration. Specifically, local models trained on graphs with high homophily tend to capture low-frequency information, whereas local models trained on graphs with low homophily tend to capture high-frequency information. To effectively deal with homophily heterophily, we introduce the spectral Graph Neural Network (GNN) and propose a novel Federated learning method by mining Graph Spectral Properties (FedGSP). On one hand, our proposed FedGSP enables clients to share generic spectral properties (i.e., low-frequency information), allowing all clients to benefit through collaboration. On the other hand, inspired by our theoretical findings, our proposed FedGSP allows clients to complement non-generic spectral properties by acquiring the spectral properties they lack (i.e., high-frequency information), thereby obtaining additional information gain. Extensive experiments conducted on six homophilic and five heterophilic graph datasets, across both non-overlapping and overlapping settings, validate the superiority of our method over eleven state-of-the-art methods. Notably, our FedGSP outperforms the second-best method by an average margin of 3.28% on all heterophilic datasets.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 36 of its 51 references that are in the map. First posted on arXiv 19 Feb 2025.

Builds on

36 of 51 references.

References · 36

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  5. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  6. 2020Personalized Federated Learning with Moreau Envelopescited by 618
  7. 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 595
  8. 2019Federated Learning with Personalization Layerscited by 541
  9. 2021Towards Personalized Federated Learningcited by 464
  10. 2021No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Datacited by 241
  11. 2021BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximationcited by 195
  12. 2022How Powerful are Spectral Graph Neural Networkscited by 169
24 more
  1. 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 161
  2. 2018Federated Meta-Learning with Fast Convergence and Efficient Communicationcited by 155
  3. 2021Subgraph Federated Learning with Missing Neighbor Generationcited by 132
  4. 2022FedALA: Adaptive Local Aggregation for Personalized Federated Learningcited by 122
  5. 2021Federated Graph Classification over Non-IID Graphscited by 114
  6. 2023Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospectscited by 99
  7. 2023Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmarkcited by 99
  8. 2022Characterizing Graph Datasets for Node Classification: Homophily-Heterophily Dichotomy and Beyondcited by 60
  9. 2022Personalized Subgraph Federated Learningcited by 54
  10. 2024FedGTA: Topology-aware Averaging for Federated Graph Learningcited by 44
  11. 2023Generalizable Heterogeneous Federated Cross-Correlation and Instance Similarity Learningcited by 40
  12. 2023Graph Neural Networks with Learnable and Optimal Polynomial Basescited by 36
  13. 2024Federated Graph Semantic and Structural Learningcited by 30
  14. 2022FedFM: Anchor-based Feature Matching for Data Heterogeneity in Federated Learningcited by 27
  15. 2024FedTAD: Topology-aware Data-free Knowledge Distillation for Subgraph Federated Learningcited by 27
  16. 2024AdaFGL: A New Paradigm for Federated Node Classification with Topology Heterogeneitycited by 25
  17. 2022Rethinking Data Heterogeneity in Federated Learning: Introducing a New Notion and Standard Benchmarkscited by 24
  18. 2024How Universal Polynomial Bases Enhance Spectral Graph Neural Networks: Heterophily, Over-smoothing, and Over-squashingcited by 24
  19. 2024FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preferencecited by 16
  20. 2024Modeling Inter-Intra Heterogeneity for Graph Federated Learningcited by 12
  21. 2022Hyperspectral Image Classification With Contrastive Graph Convolutional Networkcited by 8
  22. 2024Balancing Similarity and Complementarity for Federated Learningcited by 7
  23. 2023Atom-Motif Contrastive Transformer for Molecular Property Predictioncited by 4
  24. 2024A Blockchain-based Reliable Federated Meta-learning for Metaverse: A Dual Game Frameworkcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Heterogeneity-Aware Knowledge Sharing for Graph Federated Learningcited by 1
  2. 2026Low-pass Personalized Subgraph Federated Recommendationcited by 0
  3. 2026Graph Federated Unlearning for Privacy Preservationcited by 0
  4. 2026Beyond Rigid Alignment: Graph Federated Learning via Dual Manifold Calibrationcited by 0