Scholarlink

In scenarios where the data distribution amongst Federated Learning (FL) participants is Non-Independent and Identically distributed (Non-IID), FL suffers from the well-known problem of data heterogeneity. This leads to significantly degraded FL performance, as the global model tends to struggle to converge. To solve this problem, we propose Differentially Private Synthetic Data Aided Federated Learning Using Foundation Models (DPSDA-FL) - a novel data augmentation strategy that aids in homogenizing the local data present on the clients’ side. DPSDA-FL improves the training of the local models by leveraging differentially private synthetic data generated from foundation models. We demonstrate the effectiveness of our approach by evaluating it on the benchmark image dataset: CIFAR-10. Our experimental results show that DPSDA-FL can improve the global model’s class recall and classification accuracy by up to 26% and 9%, respectively, in FL with Non-IID issues.

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

Synthetic Data Aided Federated Learning Using Foundation Models

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Fatima Z. Abacha,
  • Sin G. Teo,
  • Lucas C. Cordeiro,
  • Mustafa A. Mustafa

摘要

In scenarios where the data distribution amongst Federated Learning (FL) participants is Non-Independent and Identically distributed (Non-IID), FL suffers from the well-known problem of data heterogeneity. This leads to significantly degraded FL performance, as the global model tends to struggle to converge. To solve this problem, we propose Differentially Private Synthetic Data Aided Federated Learning Using Foundation Models (DPSDA-FL) - a novel data augmentation strategy that aids in homogenizing the local data present on the clients’ side. DPSDA-FL improves the training of the local models by leveraging differentially private synthetic data generated from foundation models. We demonstrate the effectiveness of our approach by evaluating it on the benchmark image dataset: CIFAR-10. Our experimental results show that DPSDA-FL can improve the global model’s class recall and classification accuracy by up to 26% and 9%, respectively, in FL with Non-IID issues.