mlsanityData to 14 Oct 2026

Subgraph Federated Learning for Local Generalization

arXiv 2503.03995 ↗First posted 6 Mar 2025cs.LG cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) on graphs enables collaborative model training to enhance performance without compromising the privacy of each client. However, existing methods often overlook the mutable nature of graph data, which frequently introduces new nodes and leads to shifts in label distribution. Since they focus solely on performing well on each client's local data, they are prone to overfitting to their local distributions (i.e., local overfitting), which hinders their ability to generalize to unseen data with diverse label distributions. In contrast, our proposed method, FedLoG, effectively tackles this issue by mitigating local overfitting. Our model generates global synthetic data by condensing the reliable information from each class representation and its structural information across clients. Using these synthetic data as a training set, we alleviate the local overfitting problem by adaptively generalizing the absent knowledge within each local dataset. This enhances the generalization capabilities of local models, enabling them to handle unseen data effectively. Our model outperforms baselines in our proposed experimental settings, which are designed to measure generalization power to unseen data in practical scenarios. Our code is available at https://github.com/sung-won-kim/FedLoG

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 38 of its 58 references that are in the map. First posted on arXiv 6 Mar 2025.

Builds on

38 of 58 references.

References · 38

  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. 2022Generative Adversarial Networkscited by 5,627
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  6. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,245
  7. 2019Deep Leakage from Gradientscited by 1,021
  8. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
  9. 2015Image-based Recommendations on Styles and Substitutescited by 706
  10. 2020Long-tail learning via logit adjustmentcited by 618
  11. 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 568
  12. 2020Self-supervised Graph Learning for Recommendationcited by 305
26 more
  1. 2020Equalization Loss for Long-Tailed Object Recognitioncited by 285
  2. 2021Graph Condensation for Graph Neural Networkscited by 150
  3. 2021GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networkscited by 147
  4. 2021Subgraph Federated Learning with Missing Neighbor Generationcited by 132
  5. 2022Federated Learning with Label Distribution Skew via Logits Calibrationcited by 109
  6. 2021FedMix: Approximation of Mixup under Mean Augmented Federated Learningcited by 108
  7. 2022Condensing Graphs via One-Step Gradient Matchingcited by 100
  8. 2020FedGAN: Federated Generative Adversarial Networks for Distributed Datacited by 90
  9. 2022Federated Learning on Non-IID Graphs via Structural Knowledge Sharingcited by 88
  10. 2021Preservation of the Global Knowledge by Not-True Distillation in Federated Learningcited by 87
  11. 2023FedDisco: Federated Learning with Discrepancy-Aware Collaborationcited by 67
  12. 2020XOR Mixup: Privacy-Preserving Data Augmentation for One-Shot Federated Learningcited by 58
  13. 2023Revisiting Weighted Aggregation in Federated Learning with Neural Networkscited by 58
  14. 2023No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifiercited by 55
  15. 2022Personalized Subgraph Federated Learningcited by 54
  16. 2022Federated Graph Neural Networks: Overview, Techniques and Challengescited by 52
  17. 2024An Aggregation-Free Federated Learning for Tackling Data Heterogeneitycited by 33
  18. 2022LTE4G: Long-Tail Experts for Graph Neural Networkscited by 30
  19. 2023CUDA: Curriculum of Data Augmentation for Long-Tailed Recognitioncited by 30
  20. 2020Mix2FLD: Downlink Federated Learning After Uplink Federated Distillation With Two-Way Mixupcited by 29
  21. 2022Meta Knowledge Condensation for Federated Learningcited by 26
  22. 2023The Best of Both Worlds: Accurate Global and Personalized Models through Federated Learning with Data-Free Hyper-Knowledge Distillationcited by 25
  23. 2022FedGCN: Convergence-Communication Tradeoffs in Federated Training of Graph Convolutional Networkscited by 24
  24. 2023Learning How to Propagate Messages in Graph Neural Networkscited by 23
  25. 2021FedDPGAN: Federated Differentially Private Generative Adversarial Networks Framework for the Detection of COVID-19 Pneumoniacited by 22
  26. 2024Theoretical and Empirical Insights into the Origins of Degree Bias in Graph Neural Networkscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 4.

6 papers.

  1. 2025A Comprehensive Data-centric Overview of Federated Graph Learningcited by 7
  2. 2025Towards Unbiased Federated Graph Learning: Label and Topology Perspectivescited by 1
  3. 2026Causality-inspired Federated Learning for Dynamic Spatio-Temporal Graphscited by 1
  4. 2026Federated Concept-Based Models: Interpretable models with distributed supervisioncited by 0
  5. 2026Representation-Aligned Multi-Scale Personalization for Federated Learningcited by 0
  6. 2026From Data Heterogeneity to Convergence: A Data-Centric Review of Federated Learningcited by 0