Scholarlink

<p>Statistical heterogeneity and personalization remain key challenges in Federated Learning (FL). We propose FedDWl2, a novel FL method that combines dynamic weight aggregation with L2 regularization to address these issues. Specifically, the dynamic weight aggregation module adaptively adjusts the weights of global and local models according to each client’s data distribution, effectively capturing client-specific feature information and alleviating the impact of data heterogeneity (e.g., feature space shift). Meanwhile, L2 regularization is integrated to mitigate overfitting, enhance the generalization ability of the global model, and further assist in personalized model optimization by balancing the consistency between the global model and local models. FedDWl2 dynamically adjusts the weights of global and local models based on each client’s data distribution and employs L2 regularization to mitigate overfitting. Experiments on benchmark datasets such as CIFAR-10 and MNIST demonstrate that FedDWl2 achieves an average improvement of 0.5%-1.2% in test accuracy compared to state-of-the-art methods. Additionally, applying the dynamic weight aggregation module to other FL frameworks further validates its effectiveness and generalizability. Our results highlight FedDWl2’s ability to handle data heterogeneity while enhancing model personalization across clients.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

FedDWL2: a personalized federated learning algorithm based on a combination of dynamic aggregation and regularization

  • 期刊论文

  • 发表日期：

    2026年6月17日

查看全文
  • Haohan Ding,
  • Jiawei Tian,
  • Xiaohui Cui,
  • Zhenqi Xie,
  • Song Shen,
  • Wei Yu,
  • David I. Wilson

摘要

Statistical heterogeneity and personalization remain key challenges in Federated Learning (FL). We propose FedDWl2, a novel FL method that combines dynamic weight aggregation with L2 regularization to address these issues. Specifically, the dynamic weight aggregation module adaptively adjusts the weights of global and local models according to each client’s data distribution, effectively capturing client-specific feature information and alleviating the impact of data heterogeneity (e.g., feature space shift). Meanwhile, L2 regularization is integrated to mitigate overfitting, enhance the generalization ability of the global model, and further assist in personalized model optimization by balancing the consistency between the global model and local models. FedDWl2 dynamically adjusts the weights of global and local models based on each client’s data distribution and employs L2 regularization to mitigate overfitting. Experiments on benchmark datasets such as CIFAR-10 and MNIST demonstrate that FedDWl2 achieves an average improvement of 0.5%-1.2% in test accuracy compared to state-of-the-art methods. Additionally, applying the dynamic weight aggregation module to other FL frameworks further validates its effectiveness and generalizability. Our results highlight FedDWl2’s ability to handle data heterogeneity while enhancing model personalization across clients.