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

• URL: http://arxiv.org/abs/2507.18219v2
• Date: Tue, 05 Aug 2025 14:52:53 GMT
• Title: FedSA-GCL: A Semi-Asynchronous Federated Graph Learning Framework with Personalized Aggregation and Cluster-Aware Broadcasting
• Authors: Zhongzheng Yuan, Lianshuai Guo, Xunkai Li, Yinlin Zhu, Wenyu Wang, Meixia Qu,
• Abstract summary: Federated Graph Learning (FGL) is a distributed learning paradigm that enables collaborative training over large-scale subgraphs located on multiple local systems.<n>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.<n>We evaluate FedSA-GCL on multiple real-world graph datasets using the Louvain and Metis split algorithms, and compare it against 9 baselines.
• Score: 5.072144098417946
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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, without accounting for the unique topological properties of graph data. Directly applying these methods to graph learning can possibly result in semantic drift and representational inconsistency in 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 split algorithms, and compare it against 9 baselines. Extensive experiments demonstrate that our method achieves strong robustness and outstanding efficiency, outperforming the baselines by an average of 2.92% with the Louvain and by 3.4% with the Metis.

Related papers

• FedHERO: A Federated Learning Approach for Node Classification Task on Heterophilic Graphs [55.51300642911766]
  Federated Graph Learning (FGL) empowers clients to collaboratively train Graph neural networks (GNNs) in a distributed manner.<n>FGL methods usually require that the graph data owned by all clients is homophilic to ensure similar neighbor distribution patterns of nodes.<n>We propose FedHERO, an FGL framework designed to harness and share insights from heterophilic graphs effectively.
  arXiv  Detail & Related papers  (2025-04-29T22:23:35Z)
• FedRGL: Robust Federated Graph Learning for Label Noise [5.296582539751589]
  Federated Graph Learning (FGL) is a distributed machine learning paradigm based on graph neural networks.<n>We propose a robust federated graph learning method with label noise, termed FedRGL.<n>We show that FedRGL outperforms 12 baseline methods across various noise rates, types, and numbers of clients.
  arXiv  Detail & Related papers  (2024-11-28T04:37:04Z)
• Towards Federated Graph Learning in One-shot Communication [27.325478113745206]
  Federated Graph Learning (FGL) has emerged as a promising paradigm for breaking data silos among distributed private graphs.<n>One-shot Federated Learning (OFL) enables collaboration in a single round, but existing OFL methods are ineffective for graph data.<n>We propose the first $textbfO-pFGL$ method ($textbfO-pFGL$) for node classification, compatible with Secure Aggregation protocols for privacy preservation.
  arXiv  Detail & Related papers  (2024-11-18T05:59:29Z)
• Personalized Federated Learning for Cross-view Geo-localization [49.40531019551957]
  We propose a methodology combining Federated Learning (FL) with Cross-view Image Geo-localization (CVGL) techniques. Our method implements a coarse-to-fine approach, where clients share only the coarse feature extractors while keeping fine-grained features specific to local environments. Results demonstrate that our federated CVGL method achieves performance close to centralized training while maintaining data privacy.
  arXiv  Detail & Related papers  (2024-11-07T13:25:52Z)
• FedGraph: A Research Library and Benchmark for Federated Graph Learning [41.01586455573981]
  Federated graph learning is an emerging field with significant practical challenges.<n>We introduce FedGraph, a research library designed for practical distributed training.<n>FedGraph supports a range of state-of-the-art graph learning methods and includes a monitoring class that evaluates system performance.
  arXiv  Detail & Related papers  (2024-10-08T20:18:18Z)
• FedGTA: Topology-aware Averaging for Federated Graph Learning [44.11777886421429]
  Federated Graph Learning (FGL) is a distributed machine learning paradigm that enables collaborative training on large-scale subgraphs. Most FGL optimization strategies ignore graph structure, presenting dissatisfied performance and slow convergence. We propose Federated Graph Topology-aware Aggregation (FedGTA), a personalized optimization strategy that optimize through topology-aware local smoothing confidence and mixed neighbor features.
  arXiv  Detail & Related papers  (2024-01-22T08:31:53Z)
• AdaFGL: A New Paradigm for Federated Node Classification with Topology Heterogeneity [44.11777886421429]
  Federated Graph Learning (FGL) has attracted significant attention as a distributed framework based on graph neural networks. We introduce the concept of structure Non-iid split and then present a new paradigm called underlineAdaptive underlineFederated underlineGraph underlineLearning (AdaFGL) Our proposed AdaFGL outperforms baselines by significant margins of 3.24% and 5.57% on community split and structure Non-iid split, respectively.
  arXiv  Detail & Related papers  (2024-01-22T08:23:31Z)
• FedLALR: Client-Specific Adaptive Learning Rates Achieve Linear Speedup for Non-IID Data [54.81695390763957]
  Federated learning is an emerging distributed machine learning method. We propose a heterogeneous local variant of AMSGrad, named FedLALR, in which each client adjusts its learning rate. We show that our client-specified auto-tuned learning rate scheduling can converge and achieve linear speedup with respect to the number of clients.
  arXiv  Detail & Related papers  (2023-09-18T12:35:05Z)
• Learning Strong Graph Neural Networks with Weak Information [64.64996100343602]
  We develop a principled approach to the problem of graph learning with weak information (GLWI) We propose D$2$PT, a dual-channel GNN framework that performs long-range information propagation on the input graph with incomplete structure, but also on a global graph that encodes global semantic similarities.
  arXiv  Detail & Related papers  (2023-05-29T04:51:09Z)
• Localized Contrastive Learning on Graphs [110.54606263711385]
  We introduce a simple yet effective contrastive model named Localized Graph Contrastive Learning (Local-GCL) In spite of its simplicity, Local-GCL achieves quite competitive performance in self-supervised node representation learning tasks on graphs with various scales and properties.
  arXiv  Detail & Related papers  (2022-12-08T23:36:00Z)
• Effective and Efficient Graph Learning for Multi-view Clustering [173.8313827799077]
  We propose an effective and efficient graph learning model for multi-view clustering. Our method exploits the view-similar between graphs of different views by the minimization of tensor Schatten p-norm. Our proposed algorithm is time-economical and obtains the stable results and scales well with the data size.
  arXiv  Detail & Related papers  (2021-08-15T13:14:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.