Personalized federated learning (PFL) addresses the significant challenge of non-independent and identically distributed (non-IID) data across clients in federated learning (FL). Our proposed framework, “FairDPFL-SCS: Fair Dynamic Personalized Federated Learning with Strategic Client Selection”, marks a notable advancement in this domain. By integrating dynamic learning rate adjustments and a strategic client selection mechanism, our approach effectively mitigates the challenges posed by non-IID data while enhancing model personalization, fairness, and efficiency. We evaluated FairDPFL-SCS using standard datasets, including MNIST, FashionMNIST, and SVHN, employing architectures like VGG and CNN. Our model achieved impressive results, attaining 99.04% accuracy on MNIST, 89.19% on FashionMNIST, and 90.9% on SVHN. These results represent a substantial improvement over existing methods, including a highest increase of 16.74% in accuracy on SVHN when compared to the best-performing benchmark methods. In particular, our method also demonstrated lower fairness variance, presenting the importance of fairness in model personalization, a frequently overlooked aspect in FL research. Through extensive experiments, we validate the superior performance of FairDPFL-SCS compared to benchmark PFL approaches, highlighting significant improvements over state-of-the-art methods. This work represents a promising step forward in the field of federated learning, offering a comprehensive solution to the challenges presented by non-IID data while prioritizing fairness and efficiency in model personalization.

中文翻译：

---

FairDPFL-SCS：公平动态个性化联邦学习，具有战略性客户选择功能，可提高准确性和公平性


个性化联合学习 （PFL） 解决了联邦学习 （FL） 中跨客户端的非独立和相同分布 （non-IID） 数据的重大挑战。我们提出的框架“FairDPFL-SCS：具有战略客户选择的公平动态个性化联邦学习”标志着该领域的显着进步。通过整合动态学习率调整和战略客户选择机制，我们的方法有效地缓解了非 IID 数据带来的挑战，同时增强了模型的个性化、公平性和效率。我们使用标准数据集评估了 FairDPFL-SCS，包括 MNIST 、 FashionMNIST 和 SVHN ，采用 VGG 和 CNN 等架构。我们的模型取得了令人印象深刻的结果，在 MNIST 上获得了 99.04% 的准确率，在 FashionMNIST 上获得了 89.19% 的准确率，在 SVHN 上获得了 90.9% 的准确率。与现有方法相比，这些结果有了实质性的改进，包括与性能最佳的基准方法相比，SVHN 的准确率最高提高了 16.74%。特别是，我们的方法还显示出较低的公平性方差，展示了公平性在模型个性化中的重要性，这是 FL 研究中经常被忽视的方面。通过广泛的实验，我们验证了 FairDPFL-SCS 与基准 PFL 方法相比的卓越性能，突出了与最先进方法相比的显着改进。这项工作代表了联邦学习领域向前迈出的一大步，为非 IID 数据带来的挑战提供了全面的解决方案，同时优先考虑模型个性化的公平性和效率。