ORDERS: An Empirical Study of Norm-Rank Aggregation for Personalized Federated Learning

Key points

• 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.1
• 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.1
• 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.1
• Ablations provide limited, endpoint-dependent evidence for norm ranking and alignment, and no clear benefit from perturbations.1

Sources (1)

• [1]ORDERS: An Empirical Study of Norm-Rank Aggregation for Personalized Federated Learning
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 04:31 PM

  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.

Extractive summary: sentences quoted from the sources.