通过动态阈值复用旧模型更新，显著减少联邦学习通信开销。
DG-FedReuse: Proxy-Gradient-Gated Cached-Update Reuse with Matched Sparse Uplink Accounting
- 基于梯度差异代理判断是否复用缓存更新，控制老化与新鲜客户端比例。
- 在90轮预算下节省83.36%-85.42%的上行传输数据量，优于基准方法。
- 适合对通信效率敏感、容忍轻微精度波动的分布式训练场景。
联邦学习频繁进行本地优化和模型更新传输。本文提出DG-FedReuse，一种模拟器级机制：当随机头部梯度差异代理低于轮次相关阈值时，允许部分客户端贡献衰减年龄的缓存更新。硬性缓存年龄限制与最小新客户端配额约束复用行为，新鲜更新采用自适应逐张量Top-K数值表示。实验涵盖六种图像分类数据集、50个虚拟客户端、狄利克雷标签异质性（α=0.5）及三个种子。在90轮共同预算下，DG-FedReuse实现83.36%-85.42%的建模更新-数据字段上行节省，优于匹配的Top-K FedAvg（76.88%）；种子对齐的准确率差异为-5.29至-0.14个百分点。最佳观测测试精度在受控检查点条件下保留为探索性归档证据，相对匹配的FedAvg变化范围为-2.38至+0.45个百分点。对称密集模型下行敏感性将主要节省降至41.68%-42.71%，相对于Top-K FedAvg的增量收益仅为3.24%-4.27个百分点，表明通信结论依赖于会计边界。本研究刻画了所提复用规则在实现模拟器中的表现；未建立无偏泛化、端到端带宽缩减、运行时间或能耗节省、更快收敛，或优于现有过时更新与懒惰聚合方法的结论。
原文摘要 · Abstract (English)
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.
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。