Metraipolis › archive › dc_7b292be45f3e
One-shot federated unsupervised domain adaptation with Smoothed Knowledge Distillation and teacher refinement — arXiv:2610.30646
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.30646
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-23T15:15:02.931Z
- SHA-256 of the archived text
a498470215472a9fcd3ee5b1880916a0fc623a462e95fd02ba54c75618a523ed- Stable URL of this page
https://metraipolis.com/documento/dc_7b292be45f3e
How to cite
One-shot federated unsupervised domain adaptation with Smoothed Knowledge Distillation and teacher refinement — arXiv:2610.30646 — arXiv (en), https://arxiv.org/abs/2610.30646 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7b292be45f3e (Metraipolis archive dc_7b292be45f3e, sha256 a498470215472a9fcd3ee5b1880916a0fc623a462e95fd02ba54c75618a523ed)
BibTeX
@misc{dc7b292be45f3e,
title = {One-shot federated unsupervised domain adaptation with Smoothed Knowledge Distillation and teacher refinement — arXiv:2610.30646},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.30646},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7b292be45f3e; sha256 a498470215472a9fcd3ee5b1880916a0fc623a462e95fd02ba54c75618a523ed},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.30646. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Federated unsupervised domain adaptation (FUDA) addresses the challenge of adapting models to an unlabeled target domain using decentralized source domains while preserving data privacy. However, existing FUDA methods typically require multiple communication rounds, rely on complex aggregation strategies, and often struggle with noisy pseudo labels and inconsistent source knowledge. To address these challenges, we propose SKD-ETR, a novel one-shot FUDA framework that combines Smoothed Knowledge Distillation (SKD) and Exponential moving average-based Teacher Refinement (ETR). SKD trains a student model on the target domain using smoothed soft pseudo labels generated by the ensemble of source models. This reduces overconfidence, mitigates noise, and improves robustness. ETR further refines each source model by interpolating its parameters toward the student via exponential moving average (EMA), thereby transferring target-domain knowledge back to the teachers. This bidirectional refinement enhances pseudo-label quality and student generalization without additional communication overhead. SKD-ETR eliminates complex aggregation by initializing the student model randomly and performing a single-round distillation process. Extensive experiments on OfficeHome, Office-Caltech, and DomainNet demonstrate that SKD-ETR achieves competitive performance while being communication- and computation-efficient, and robust under noisy supervision. The code for this paper is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.30646 — 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 2026-10-23T15:09:08.541Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).