按客户端标签分布动态分配生成预算，显著降低计算成本同时提升联邦学习精度。
WHERE to Generate Matters: Budget-Aware Synthetic Augmentation for Label Skewed Federated Learning
- 基于本地标签分布自适应分配每类生成预算，决定生成量与分布位置。
- 生成预算减少94.1%仍恢复全平衡的大部分准确率增益。
- 适合资源受限且标签分布不均的联邦学习场景，尤其关注效率与公平性。
联邦学习中的标签偏斜导致客户端漂移并降低全局准确率。合成数据增强可缓解此不平衡，但完全类别平衡需高昂计算成本。我们提出FedEAS，一种策略：根据各客户端本地标签分布，自适应分配每类生成预算。该预算共同决定客户端生成多少样本及样本生成位置。总生成预算由各客户端预算累加得出，而非预先固定。FedEAS在仅需94.1%生成预算的情况下，恢复了全类别平衡的大部分准确率增益；在相同总生成预算下，相较于均匀分配，在CIFAR-10和CIFAR-100上最高提升18.82%。
原文摘要 · Abstract (English)
Label skew in federated learning (FL) causes client drift and degrades global accuracy. Synthetic data augmentation can reduce this imbalance; however, full class balancing requires substantial computation cost. We propose FedEAS, a policy that assigns each client an entropy-adaptive per-class generation budget computed from its local label distribution. The budget jointly decides \emph{how much} each client generates and \emph{WHERE} the samples go. Accordingly, the total generation budget follows from the per-client budgets rather than being fixed in advance. FedEAS recovers most of the accuracy gain of full class balancing while reducing the generation budget by 94.1\%. At the same total generation budget, it outperforms Uniform allocation by up to 18.82\% across CIFAR-10 and CIFAR-100.
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。