通过自适应提升机制，让联邦学习更公平高效。
FeDABoost: Fairness Aware Federated Learning with Adaptive Boosting
- 根据本地误差率动态加权聚合，优先采纳表现好的客户端
- 对表现差的客户端调整焦点损失，重点训练难分类样本
- 在多个数据集上兼顾公平性与性能，适合非独立同分布场景
本工作聚焦于在非独立同分布（non-IID）环境下提升联邦学习（FL）的性能与公平性，通过优化模型聚合并增强表现较差客户端的训练。我们提出 FeDABoost，一种融合动态提升机制与自适应梯度聚合策略的新型联邦学习框架。受多类 AdaBoost（SAMME）权重机制启发，该聚合方法为本地误差率较低的客户端分配更高权重，从而提升其对全局模型的贡献可靠性。同时，FeDABoost 动态调整焦点损失的关注参数，强化本地训练中难以分类样本的学习。我们在 MNIST、FEMNIST 与 CIFAR10 三个基准数据集上评估了 FeDABoost，与 FedAvg 及 Ditto 进行对比。结果表明，FeDABoost 在提升公平性的同时保持了具有竞争力的性能。
原文摘要 · Abstract (English)
This work focuses on improving the performance and fairness of Federated Learning (FL) in non IID settings by enhancing model aggregation and boosting the training of underperforming clients. We propose FeDABoost, a novel FL framework that integrates a dynamic boosting mechanism and an adaptive gradient aggregation strategy. Inspired by the weighting mechanism of the Multiclass AdaBoost (SAMME) algorithm, our aggregation method assigns higher weights to clients with lower local error rates, thereby promoting more reliable contributions to the global model. In parallel, FeDABoost dynamically boosts underperforming clients by adjusting the focal loss focusing parameter, emphasizing hard to classify examples during local training. We have evaluated FeDABoost on three benchmark datasets MNIST, FEMNIST, and CIFAR10, and compared its performance with those of FedAvg and Ditto. The results show that FeDABoost achieves improved fairness and competitive performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。