Metraipolis › archive › dc_4fa815dbd92b
D-FROST: Decentralized Federated pRompt-tuning via Optimal tranSporT for Non-IID and Imbalanced Data — arXiv:2609.01802
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.01802
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T04:59:15.702Z
- SHA-256 of the archived text
cd16c3e7a04084dd936e5e2e8a9170c2ef31a43360c5f223827107c2efa1a865- Stable URL of this page
https://metraipolis.com/documento/dc_4fa815dbd92b
How to cite
D-FROST: Decentralized Federated pRompt-tuning via Optimal tranSporT for Non-IID and Imbalanced Data — arXiv:2609.01802 — arXiv (en), https://arxiv.org/abs/2609.01802 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4fa815dbd92b (Metraipolis archive dc_4fa815dbd92b, sha256 cd16c3e7a04084dd936e5e2e8a9170c2ef31a43360c5f223827107c2efa1a865)
BibTeX
@misc{dc4fa815dbd92b,
title = {D-FROST: Decentralized Federated pRompt-tuning via Optimal tranSporT for Non-IID and Imbalanced Data — arXiv:2609.01802},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.01802},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4fa815dbd92b; sha256 cd16c3e7a04084dd936e5e2e8a9170c2ef31a43360c5f223827107c2efa1a865},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01802. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Prompt tuning provides a parameter-efficient way to adapt foundation models (FMs) by freezing the pretrained backbone and updating only a small set of learnable prompts. This property makes prompt tuning especially suitable for decentralized federated learning (DFL), where exchanging full-model updates can be prohibitively expensive. However, prompt tuning in DFL introduces new challenges. Prompt sets learned from heterogeneous local data may not be index-wise aligned, making standard decentralized averaging unsuitable. In addition, the algorithm should be theoretically guaranteed to achieve consensus and make progress toward the shared objective. In this work, we provide the first study of prompt tuning in DFL. We formulate decentralized prompt tuning as a Wasserstein-based optimization problem over prompt measures, which captures the set-valued structure of prompts. We then propose D-FROST, an optimal-transport-based (OT-based) decentralized prompt-tuning algorithm that merges neighborhood prompts into compact representative prompt sets through transportation-based matching. We further analyze D-FROST by bounding the Wasserstein consensus error across clients, and establishing convergence of the network-level prompt barycenter to a neighborhood of stationarity. Experiments under heterogeneous client data demonstrate the effectiveness of D-FROST for decentralized prompt tuning. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-03 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.01802 — 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 2026-10-17T04:09:43.292Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).