Metraipolis › archive › dc_ffc1d36218bf

SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks — arXiv:2608.10144

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.10144
License (as archived)
CC0-1.0
Archived
2026-10-19T06:14:37.878Z
SHA-256 of the archived text
9c2d32a7f6d41d4748c08e1433e2566b0a59f03d0e7db40840f3073aa72b5859
Stable URL of this page
https://metraipolis.com/documento/dc_ffc1d36218bf

How to cite

SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks — arXiv:2608.10144 — arXiv (en), https://arxiv.org/abs/2608.10144 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ffc1d36218bf (Metraipolis archive dc_ffc1d36218bf, sha256 9c2d32a7f6d41d4748c08e1433e2566b0a59f03d0e7db40840f3073aa72b5859)
BibTeX
@misc{dcffc1d36218bf,
  title = {SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks — arXiv:2608.10144},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.10144},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ffc1d36218bf; sha256 9c2d32a7f6d41d4748c08e1433e2566b0a59f03d0e7db40840f3073aa72b5859},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10144. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We consider federated parameter efficient fine-tuning of large neural networks with low-rank adaptation (LoRA,~Hu et al.\ 2022). Combining LoRA with federated PEFT introduces challenges absent from either setting alone: clients may use different LoRA ranks, making their factor matrices dimension-incompatible, and factor-wise averaging suffers from a bilinear mismatch. We propose SeFoRA, a sketch-aggregated federated LoRA algorithm in which each client transmits a linear sketch of its local updates, enabling direct aggregation at the federator. As a result, SeFoRA alleviates the bilinear mismatch, and allows for aggregation in a small subspace of the full model. We introduce a rank-homogeneous version called SeFoRA-Ho which allows for direct adapter aggregation in this setting. We prove convergence to a neighborhood of the first-order stationary point at rate $\cO(1/T)$ for the rank-homogeneous setting. Numerical experiments on fine-tuning RoBERTa-Large on GLUE datasets show how our algorithms outperform the state-of-the-art.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-12 in cs.DC).
Categorie arXiv: Machine Learning (cs.LG) ; Distributed, Parallel, and Cluster Computing (cs.DC).
Pagina del lavoro: https://arxiv.org/abs/2608.10144 — 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 2026-10-19T06:09:08.098Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).