{"ID":6138545,"CreatedAt":"2026-07-09T01:07:32.349475501Z","UpdatedAt":"2026-07-10T08:15:11.905439937Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.06616","arxiv_id":"2607.06616","title":"WHERE to Generate Matters: Budget-Aware Synthetic Augmentation for Label Skewed Federated Learning","abstract":"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.","short_abstract":"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 compute...","url_abs":"https://arxiv.org/abs/2607.06616","url_pdf":"https://arxiv.org/pdf/2607.06616v1","authors":"[\"Sangwoo Lee\",\"Sunghwan Park\",\"Jaewoo Lee\"]","published":"2026-07-07T08:25:04Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"cs.CV\"]","methods":"[]","has_code":false}