个性化联邦学习新方法提升多数据集准确率
Personalized Federated Learning through Global Knowledge Distillation and Local Head Adaptation
这个研究方法挺有意思，用全局知识蒸馏和本地头部适应来处理联邦学习中的统计异质性问题，效果比传统方法好不少。
这项研究提出了一种名为pFedKDH的新方法，通过聚合共享主干并保留客户端特定头部，在MNIST、Fashion-MNIST、CIFAR10和CIFAR100等数据集上实现了最佳准确率，在某些情况下比最弱基线高出37.67%。
Personalized Federated Learning through Global Knowledge Distillation and Local Head Adaptation
Statistical heterogeneity limits federated learning when a single global classifier cannot represent client-specific label distributions. In this work, we propose Personalized Federated Knowledge Distillation with Head Adaptation (pFedKDH), which aggregates only the shared backbone, keeps persistent client-specific heads, and uses a recalibrated global head as a teacher during local training. Across MNIST, Fashion-MNIST, CIFAR10, and CIFAR100 under class-wise Dirichlet partitions, pFedKDH obtains the best accuracy in most settings, with accuracy gaps up to 37.67\% over the weakest baseline and consistently low standard deviation across repetitions. Component-wise diagnostics and convergence results support the role of persistent heads and distillation-guided local optimization under label-skewed data.