Sharpness-aware Federated Graph Learning

• URL: http://arxiv.org/abs/2512.16247v1
• Date: Thu, 18 Dec 2025 06:57:13 GMT
• Title: Sharpness-aware Federated Graph Learning
• Authors: Ruiyu Li, Peige Zhao, Guangxia Li, Pengcheng Wu, Xingyu Gao, Zhiqiang Xu,
• Abstract summary: One of many impediments to applying graph neural networks (GNNs) to large-scale real-world graph data is the challenge of centralized training.<n> Federated graph learning (FGL) addresses this by enabling collaborative GNN model training without sharing private data.
• Score: 16.148982247077157
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: One of many impediments to applying graph neural networks (GNNs) to large-scale real-world graph data is the challenge of centralized training, which requires aggregating data from different organizations, raising privacy concerns. Federated graph learning (FGL) addresses this by enabling collaborative GNN model training without sharing private data. However, a core challenge in FGL systems is the variation in local training data distributions among clients, known as the data heterogeneity problem. Most existing solutions suffer from two problems: (1) The typical optimizer based on empirical risk minimization tends to cause local models to fall into sharp valleys and weakens their generalization to out-of-distribution graph data. (2) The prevalent dimensional collapse in the learned representations of local graph data has an adverse impact on the classification capacity of the GNN model. To this end, we formulate a novel optimization objective that is aware of the sharpness (i.e., the curvature of the loss surface) of local GNN models. By minimizing the loss function and its sharpness simultaneously, we seek out model parameters in a flat region with uniformly low loss values, thus improving the generalization over heterogeneous data. By introducing a regularizer based on the correlation matrix of local representations, we relax the correlations of representations generated by individual local graph samples, so as to alleviate the dimensional collapse of the learned model. The proposed \textbf{S}harpness-aware f\textbf{E}derated gr\textbf{A}ph \textbf{L}earning (SEAL) algorithm can enhance the classification accuracy and generalization ability of local GNN models in federated graph learning. Experimental studies on several graph classification benchmarks show that SEAL consistently outperforms SOTA FGL baselines and provides gains for more participants.

Related papers

• Causal Neighbourhood Learning for Invariant Graph Representations [8.854365724044984]
  We propose Causal Neighbourhood Learning with Graph Neural Networks (CNL-GNN), a novel framework that performs causal interventions on graph structure.<n>CNL-GNN effectively identifies and preserves causally relevant connections and reduces spurious influences.<n>Our approach improves causal graph learning beyond traditional feature-based methods, resulting in a robust classification model.
  arXiv  Detail & Related papers  (2026-02-20T01:52:58Z)
• GraphFedMIG: Tackling Class Imbalance in Federated Graph Learning via Mutual Information-Guided Generation [19.1700923188257]
  Federated graph learning (FGL) enables multiple clients to collaboratively train powerful graph neural networks without sharing their private, decentralized graph data.<n>We propose GraphFedMIG, a novel FGL framework that reframes the problem as a federated generative data augmentation task.<n>We conduct extensive experiments on four real-world datasets, and the results demonstrate the superiority of the proposed GraphFedMIG compared with other baselines.
  arXiv  Detail & Related papers  (2025-08-14T09:16:56Z)
• Graph Out-of-Distribution Generalization via Causal Intervention [69.70137479660113]
  We introduce a conceptually simple yet principled approach for training robust graph neural networks (GNNs) under node-level distribution shifts. Our method resorts to a new learning objective derived from causal inference that coordinates an environment estimator and a mixture-of-expert GNN predictor. Our model can effectively enhance generalization with various types of distribution shifts and yield up to 27.4% accuracy improvement over state-of-the-arts on graph OOD generalization benchmarks.
  arXiv  Detail & Related papers  (2024-02-18T07:49:22Z)
• Learning to Reweight for Graph Neural Network [63.978102332612906]
  Graph Neural Networks (GNNs) show promising results for graph tasks. Existing GNNs' generalization ability will degrade when there exist distribution shifts between testing and training graph data. We propose a novel nonlinear graph decorrelation method, which can substantially improve the out-of-distribution generalization ability.
  arXiv  Detail & Related papers  (2023-12-19T12:25:10Z)
• Graph Out-of-Distribution Generalization with Controllable Data Augmentation [51.17476258673232]
  Graph Neural Network (GNN) has demonstrated extraordinary performance in classifying graph properties. Due to the selection bias of training and testing data, distribution deviation is widespread. We propose OOD calibration to measure the distribution deviation of virtual samples.
  arXiv  Detail & Related papers  (2023-08-16T13:10:27Z)
• Addressing the Impact of Localized Training Data in Graph Neural Networks [0.0]
  Graph Neural Networks (GNNs) have achieved notable success in learning from graph-structured data. This article aims to assess the impact of training GNNs on localized subsets of the graph. We propose a regularization method to minimize distributional discrepancies between localized training data and graph inference.
  arXiv  Detail & Related papers  (2023-07-24T11:04:22Z)
• Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning [112.69497636932955]
  Federated learning aims to train models across different clients without the sharing of data for privacy considerations. We study how data heterogeneity affects the representations of the globally aggregated models. We propose sc FedDecorr, a novel method that can effectively mitigate dimensional collapse in federated learning.
  arXiv  Detail & Related papers  (2022-10-01T09:04:17Z)
• Optimal Propagation for Graph Neural Networks [51.08426265813481]
  We propose a bi-level optimization approach for learning the optimal graph structure. We also explore a low-rank approximation model for further reducing the time complexity.
  arXiv  Detail & Related papers  (2022-05-06T03:37:00Z)
• Learn Locally, Correct Globally: A Distributed Algorithm for Training Graph Neural Networks [22.728439336309858]
  We propose a communication-efficient distributed GNN training technique named $textLearn Locally, Correct Globally$ (LLCG) LLCG trains a GNN on its local data by ignoring the dependency between nodes among different machines, then sends the locally trained model to the server for periodic model averaging. We rigorously analyze the convergence of distributed methods with periodic model averaging for training GNNs and show that naively applying periodic model averaging but ignoring the dependency between nodes will suffer from an irreducible residual error.
  arXiv  Detail & Related papers  (2021-11-16T03:07:01Z)
• Tackling the Local Bias in Federated Graph Learning [48.887310972708036]
  In Federated graph learning (FGL), a global graph is distributed across different clients, where each client holds a subgraph. Existing FGL methods fail to effectively utilize cross-client edges, losing structural information during the training. We propose a novel FGL framework to make the local models similar to the model trained in a centralized setting.
  arXiv  Detail & Related papers  (2021-10-22T08:22:36Z)

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.