ORDERS：个性化联邦学习中范数排名聚合的实证研究

中文摘要 AI 辅助

个性化联邦学习将共享表示与客户端特定的预测器相结合，但服务器加权规则的作用可能被本地训练和评估选择所掩盖。我们研究ORDERS，一种结合了共享主干网络、私有残差适配器和分类器、按更新范数降序分配的几何权重、特征对齐以及私有参数扰动的配置。服务器计算从同一广播模型获得的更新的加权和；它不会从顺序添加中获得额外的优化效果。一个完全指定的评估包含80次最终运行：八个配置、两个数据集，以及每个数据集一个固定划分上的五个训练种子。在每客户端两个类别的CIFAR-10上，ORDERS实现了$80.51 \pm 0.79\\%$的原生平均客户端准确率，而FedPer-R1为$79.02 \pm 1.42\\%$，匹配的均匀权重控制为$80.27 \pm 0.73\\%$。在常见的本地微调后，与FedPer-R1的差异缩小到0.32个百分点。在Sent140上，ORDERS达到$74.71 \pm 0.49\\%$，仅比事后客户端训练多数诊断高出0.69个百分点。消融研究提供了有限的、端点依赖的证据支持范数排名和对齐，而扰动没有明显益处。参数负载节省分别为5.47%和0.78%。

英文摘要

Personalized federated learning combines shared representations with client-specific predictors, but the contribution of a server weighting rule can be obscured by local training and evaluation choices. We study ORDERS, a configuration that combines a shared backbone, a private residual adapter and classifier, geometric weights assigned by descending update norm, feature alignment, and private-parameter perturbations. The server computes a weighted sum of updates obtained from the same broadcast model; it does not obtain an additional optimization effect from sequential addition. A fully specified evaluation comprises 80 final runs: eight configurations, two datasets, and five training seeds on one fixed partition per dataset. On two-class-per-client CIFAR-10, ORDERS achieves $80.51 \pm 0.79\%$ native mean client accuracy, compared with $79.02 \pm 1.42\%$ for FedPer-R1 and $80.27 \pm 0.73\%$ for the matched uniform-weight control. After common local fine-tuning, the difference from FedPer-R1 narrows to 0.32 percentage points. On Sent140, ORDERS reaches $74.71 \pm 0.49\%$, only 0.69 points above a post hoc client training-majority diagnostic. Ablations provide limited, endpoint-dependent evidence for norm ranking and alignment, and no clear benefit from perturbations. Parameter-payload savings are 5.47% and 0.78%, respectively.

发表机构

• The University of the West Indies（西印度群岛大学）

机构由 AI 辅助整理，请以论文原文为准。