Metraipolis › archive › dc_5e196e359f2c
ORDERS: An Empirical Study of Norm-Rank Aggregation for Personalized Federated Learning — arXiv:2610.10361
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.10361
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T12:36:22.276Z
- SHA-256 of the archived text
76ab4658fb4bc92add927d1e554cfc248b22b7dfcc0d090d6997db3eae755eb4- Stable URL of this page
https://metraipolis.com/documento/dc_5e196e359f2c
How to cite
ORDERS: An Empirical Study of Norm-Rank Aggregation for Personalized Federated Learning — arXiv:2610.10361 — arXiv (en), https://arxiv.org/abs/2610.10361 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5e196e359f2c (Metraipolis archive dc_5e196e359f2c, sha256 76ab4658fb4bc92add927d1e554cfc248b22b7dfcc0d090d6997db3eae755eb4)
BibTeX
@misc{dc5e196e359f2c,
title = {ORDERS: An Empirical Study of Norm-Rank Aggregation for Personalized Federated Learning — arXiv:2610.10361},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.10361},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5e196e359f2c; sha256 76ab4658fb4bc92add927d1e554cfc248b22b7dfcc0d090d6997db3eae755eb4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10361. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.10361 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T12:14:15.337Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).