Metraipolis › archive › dc_46eba258c15b

Rethinking Model Aggregation for Federated Learning with Domain Skew: A Knowledge-Preserving Perspective — arXiv:2611.01893

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01893
License (as archived)
CC0-1.0
Archived
2026-11-03T10:27:52.333Z
SHA-256 of the archived text
d0c5c744def97ce2556b51bd3f994e0a2d41189538b64a83b869eeb8428d8ac9
Stable URL of this page
https://metraipolis.com/documento/dc_46eba258c15b

How to cite

Rethinking Model Aggregation for Federated Learning with Domain Skew: A Knowledge-Preserving Perspective — arXiv:2611.01893 — arXiv (en), https://arxiv.org/abs/2611.01893 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_46eba258c15b (Metraipolis archive dc_46eba258c15b, sha256 d0c5c744def97ce2556b51bd3f994e0a2d41189538b64a83b869eeb8428d8ac9)
BibTeX
@misc{dc46eba258c15b,
  title = {Rethinking Model Aggregation for Federated Learning with Domain Skew: A Knowledge-Preserving Perspective — arXiv:2611.01893},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01893},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_46eba258c15b; sha256 d0c5c744def97ce2556b51bd3f994e0a2d41189538b64a83b869eeb8428d8ac9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01893. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Domain skew challenges federated learning by requiring a shared model to accommodate distinct visual distributions. Domain-specific experts can capture these distributions separately, creating an opportunity to integrate their representations in a unified predictor. We propose Federated Knowledge-Preserving Learning (FKPL), a two-stage framework that combines domain-oriented expert training with prototype-based classifier calibration. First, a one-shot subspace-based clustering procedure groups clients for intra-cluster training. The resulting expert encoders are concatenated and frozen, preserving each learned feature mapping during global integration. Second, clients interpolate their concatenated features with class-matched domain prototypes and upload the resulting virtual features. The server trains a global linear classifier on these features, concentrating classifier optimization at the server after a single feature upload. FKPL achieves average accuracies of 73.01\%, 67.00\%, and 64.51\% on Office-Caltech-10, PACS, and a four-domain subset of DomainNet, respectively. On DomainNet, its cross-domain standard deviation is 7.50 percentage points, the lowest among the evaluated methods. With the same concatenated extractor, prototype-based calibration improves average accuracy over federated classifier training by 9.99 and 14.94 percentage points on Office-Caltech-10 and PACS. These results identify classifier calibration as an effective way to combine preserved domain representations into a global predictor.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.01893 — 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 2026-11-03T10:19:50.129Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).