发表机构
Jamia Hamdard; Homi Bhabha National Institute; Variable Energy Cyclotron Centre; Gargi Memorial Institute of Technology; Maulana Abul Kalam Azad University of Technology（贾米亚·哈姆达德大学; 霍米·巴伯国家研究所; 可变能量回旋加速器中心; 加尔吉纪念技术学院; 毛拉纳·阿布尔·卡拉姆·阿扎德技术大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出DG-FedReuse机制，通过代理梯度门控缓存更新复用结合匹配稀疏上行链路核算，在联邦学习中实现更高上行链路节省，但需注意其未确立无偏泛化等优势。
AI 中文摘要
联邦学习会反复进行局部优化和模型更新传输。本研究提出DG-FedReuse，这是一种模拟器级机制，当随机头部梯度差异代理保持在轮次相关阈值以下时，允许选定客户端贡献经年龄衰减的缓存更新。该机制通过严格的缓存年龄限制和最低新鲜客户端配额来约束更新复用，而新鲜更新则采用自适应逐张量Top-K数值场表示。实验涵盖6个图像分类数据集、50个虚拟客户端、狄利克雷标签异质性（α=0.5）以及3个随机种子。在90轮的通用预算下，与匹配的Top-K FedAvg的76.88%相比，DG-FedReuse实现了83.36%-85.42%的建模更新数据场上行链路节省；种子对齐的准确率差异范围为-5.29至-0.14个百分点。在测试控制检查点下获得的最佳观测测试准确率仅作为探索性存档证据保留，与匹配的FedAvg相比，其范围为-2.38至+0.45个百分点。对称密集模型下行链路敏感性将主要节省降低至41.68%-42.71%，并将其相对于Top-K FedAvg的增量增益降低至3.24%-4.27个百分点，这表明通信结论取决于核算边界。本研究在已实现的模拟器中表征了所提出的复用规则；它未确立无偏泛化、端到端带宽减少、运行时或能源节省、更快收敛，或优于现有陈旧更新和惰性聚合方法。
英文摘要
Federated learning repeatedly incurs local optimization and model-update transmission. We study DG-FedReuse, a simulator-level mechanism that allows selected clients to contribute age-decayed cached updates when a stochastic head-gradient discrepancy proxy remains below a round-dependent threshold. A hard cache-age limit and minimum fresh-client quota constrain reuse, while fresh updates use an adaptive per-tensor Top-K numerical-field representation. Experiments cover six image-classification datasets, 50 virtual clients, Dirichlet label heterogeneity (α=0.5), and three seeds. At a common 90-round budget, DG-FedReuse yields 83.36-85.42% modeled update-data-field uplink saving, compared with 76.88% for matched Top-K FedAvg; the seed-aligned accuracy differences range from -5.29 to -0.14 percentage points. Best-observed test accuracies obtained under test-controlled checkpointing are retained only as exploratory archival evidence and range from -2.38 to +0.45 percentage points relative to matched FedAvg. A symmetric dense-model-downlink sensitivity reduces the headline saving to 41.68-F42.71% and the incremental gain over Top-K FedAvg to 3.24-4.27 percentage points, demonstrating the dependence of communication conclusions on the accounting boundary. The study characterizes the proposed reuse rule in the implemented simulator; it does not establish unbiased generalization, end-to-end bandwidth reduction, runtime or energy savings, faster convergence, or superiority over existing stale-update and lazy-aggregation methods.
