Scholarlink

This paper presents a novel training pipeline for Federated Learning (FL), enriched in two aspects, with the goal of improving accuracy. First, we exploit the generative ability of Generative Adversarial Networks (GANs) to augment the clients’ local datasets with synthetic data and second, we incorporate them into the FL training procedure with the help of Ensemble Learning. Drawing inspiration from their demonstrated potential in Deep Learning (DL), we adeptly modify these techniques to address the privacy concerns and distributed nature inherent in FL. Our proposed FL pipeline lead to a 3% and 2.5% improvement in the accuracy of the global model on the MNIST and CIFAR-10 test sets, respectively, compared to the baseline and modified versions of FedAvg. This paves the way for exploring the potential of our method in achieving similar or larger improvement in other FL algorithms.

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

On Improving Accuracy in Federated Learning Using GANs-Based Pre-training and Ensemble Learning

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Thomas Tsouparopoulos,
  • Iordanis Koutsopoulos

摘要

This paper presents a novel training pipeline for Federated Learning (FL), enriched in two aspects, with the goal of improving accuracy. First, we exploit the generative ability of Generative Adversarial Networks (GANs) to augment the clients’ local datasets with synthetic data and second, we incorporate them into the FL training procedure with the help of Ensemble Learning. Drawing inspiration from their demonstrated potential in Deep Learning (DL), we adeptly modify these techniques to address the privacy concerns and distributed nature inherent in FL. Our proposed FL pipeline lead to a 3% and 2.5% improvement in the accuracy of the global model on the MNIST and CIFAR-10 test sets, respectively, compared to the baseline and modified versions of FedAvg. This paves the way for exploring the potential of our method in achieving similar or larger improvement in other FL algorithms.