mlsanityData to 14 Oct 2026

FedSA-GCL: A Semi-Asynchronous Federated Graph Learning Framework with Personalized Aggregation and Cluster-Aware Broadcasting

arXiv 2507.18219 ↗First posted 24 Jul 2025cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated Graph Learning (FGL) is a distributed learning paradigm that enables collaborative training over large-scale subgraphs located on multiple local systems. However, most existing FGL approaches rely on synchronous communication, which leads to inefficiencies and is often impractical in real-world deployments. Meanwhile, current asynchronous federated learning (AFL) methods are primarily designed for conventional tasks such as image classification and natural language processing, consequently failing to account for the unique topological properties of graph data. Directly applying these methods to graph learning frequently results in semantic drift and representational inconsistency within the global model. To address these challenges, we propose FedSA-GCL, a semi-asynchronous federated framework that leverages both inter-client label distribution divergence and graph topological characteristics through a novel ClusterCast mechanism for efficient training. We evaluate FedSA-GCL on multiple real-world graph datasets using the Louvain and Metis algorithms and conduct comparative analysis against 10 baselines. Extensive experiments demonstrate that our method achieves superior robustness and outstanding efficiency, outperforming the baselines by an average margin of 1.9% with Louvain and 3.0% with Metis.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 36 of its 50 references that are in the map. First posted on arXiv 24 Jul 2025.

Builds on

36 of 50 references.

References · 36

  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. 2018How Powerful are Graph Neural Networks?cited by 4,393
  6. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  7. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  8. 2019Simplifying Graph Convolutional Networkscited by 1,477
  9. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
  10. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 993
  11. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 976
  12. 2021Model-Contrastive Federated Learningcited by 766
24 more
  1. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 584
  2. 2019Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networkscited by 541
  3. 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 352
  4. 2020SIGN: Scalable Inception Graph Neural Networkscited by 284
  5. 2019Asynchronous Federated Optimizationcited by 267
  6. 2020Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecastingcited by 213
  7. 2021Federated Learning with Buffered Asynchronous Aggregationcited by 190
  8. 2021Subgraph Federated Learning with Missing Neighbor Generationcited by 132
  9. 2021Federated Graph Classification over Non-IID Graphscited by 114
  10. 2019Communication-Efficient Federated Deep Learning with Asynchronous Model Update and Temporally Weighted Aggregationcited by 100
  11. 2021Asynchronous Federated Learning on Heterogeneous Devices: A Surveycited by 93
  12. 2020Scalable Graph Neural Networks via Bidirectional Propagationcited by 87
  13. 2022Graph Attention Multi-Layer Perceptroncited by 83
  14. 2022Personalized Subgraph Federated Learningcited by 54
  15. 2021Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion Networkcited by 52
  16. 2024FedGTA: Topology-aware Averaging for Federated Graph Learningcited by 44
  17. 2021FedGL: Federated Graph Learning Framework with Global Self-Supervisioncited by 34
  18. 2023TimelyFL: Heterogeneity-aware Asynchronous Federated Learning with Adaptive Partial Trainingcited by 27
  19. 2024FedTAD: Topology-aware Data-free Knowledge Distillation for Subgraph Federated Learningcited by 27
  20. 2024AdaFGL: A New Paradigm for Federated Node Classification with Topology Heterogeneitycited by 25
  21. 2024OpenFGL: A Comprehensive Benchmark for Federated Graph Learningcited by 16
  22. 2022Federated Graph Machine Learning: A Survey of Concepts, Techniques, and Applicationscited by 14
  23. 2022Pisces: Efficient Federated Learning via Guided Asynchronous Trainingcited by 8
  24. 2024FedGraph: A Research Library and Benchmark for Federated Graph Learningcited by 3

Built on by

Not cited yet.