Metraipolis › archive › dc_189eca63e5d8

FedLAFP: Low-Rank Aggregation Meets Full-Rank Personalization in Federated Fine-Tuning — arXiv:2609.37033

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.37033
License (as archived)
CC0-1.0
Archived
2026-10-07T16:23:25.641Z
SHA-256 of the archived text
458cb003635eeb23de20ea956b709f6133c7b0a5a6cd3cb155649ebcea88f667
Stable URL of this page
https://metraipolis.com/documento/dc_189eca63e5d8

How to cite

FedLAFP: Low-Rank Aggregation Meets Full-Rank Personalization in Federated Fine-Tuning — arXiv:2609.37033 — arXiv (en), https://arxiv.org/abs/2609.37033 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_189eca63e5d8 (Metraipolis archive dc_189eca63e5d8, sha256 458cb003635eeb23de20ea956b709f6133c7b0a5a6cd3cb155649ebcea88f667)
BibTeX
@misc{dc189eca63e5d8,
  title = {FedLAFP: Low-Rank Aggregation Meets Full-Rank Personalization in Federated Fine-Tuning — arXiv:2609.37033},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.37033},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_189eca63e5d8; sha256 458cb003635eeb23de20ea956b709f6133c7b0a5a6cd3cb155649ebcea88f667},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37033. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Federated parameter-efficient fine-tuning enables clients to adapt pre-trained models without sharing raw data or communicating the full model, but statistical heterogeneity makes a single global adapter insufficient for personalized prediction. Existing personalized methods typically use the same low-rank structure for both shared and private adaptation, overlooking their distinct requirements for aggregation and personalization. We propose FedLAFP, a role-aware framework that couples a compact, globally aggregated LoRA branch with a client-private, full-rank-capable RandLoRA branch. The shared branch provides an efficient interface for transferring common knowledge, whereas the private branch combines fixed random low-rank bases with learned scaling coefficients to provide expressive client-specific adaptation without additional communication. Client- and layer-specific mixing coefficients jointly fuse the two branches, and only the shared LoRA parameters are exchanged. A controlled linear study supports this role assignment: LoRA yields more aligned client updates and lower aggregation error, while RandLoRA more accurately recovers client-specific residuals. Experiments across four visual recognition benchmarks show that FedLAFP consistently outperforms local-only and federated LoRA baselines, achieving an average personalized accuracy of $86.93\%$ and exceeding the best baseline average by $1.30$ percentage points.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.37033 — 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 2026-10-07T15:54:53.582Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).