arXiv：cs.LG· Koffka Khan·· 4 小时前AI 评分33
ORDERS：个性化联邦学习范数秩聚合的实证研究
ORDERS: An Empirical Study of Norm-Rank Aggregation for Personalized Federated Learning
AI 导读
研究对个性化联邦学习配置 ORDERS 进行实证评估，该配置结合共享主干、私有残差适配器与分类器、按更新范数降序分配的几何权重、特征对齐及私有参数扰动。
正文
Abstract: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.
| Subjects: | Machine Learning (cs.LG) |
| MSC classes: | 68T05, 68T07, 68W15 |
| ACM classes: | I.2.6 |
| Cite as: | arXiv:2610.10361 [cs.LG] |
| (or arXiv:2610.10361v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.10361 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Koffka Khan [view email]
[v1]
Wed, 7 Oct 2026 16:31:44 UTC (682 KB)
来源：arXiv：cs.LG · arxiv.org