跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.13331 · v1

Stochastic Projections and Rank-Aware Learning Rates for Federated LoRA

首次提交 2026-11-10 06:58
版本更新 2026-11-10 06:58
雷达观测 2026-11-11 11:04
arXiv ↗PDF ↗

摘要

Fine-tuning large-scale foundation models across resource-constrained, distributed clients presents significant computational and communication challenges. While merging Low-Rank Adaptation (LoRA) with Federated Learning (FL) enables rank-based flexibility, the interdependence of the adaptation matrices (A\mathbf{A} and B\mathbf{B}) often complicates optimization. In this work, we theoretically demonstrate that LoRA fine-tuning with Gaussian initialization and a frozen A\mathbf{A} matrix acts as a stochastic approximation of full fine-tuning, where batch gradients are subject to a random, rank-dependent perturbation. Motivated by this insight, we propose freezing and periodically resampling A\mathbf{A} matrices at the client level. This strategy decouples the A\mathbf{A} and B\mathbf{B} gradients, diminishes LoRA low-rank constraints and reduces both computational and uplink communication overheads by 50\%, allowing for the reallocation of resources toward higher adaptation ranks. Furthermore, we show that in this frozen-A\mathbf{A} regime, the adaptation rank rr directly governs the signal-to-noise ratio (SNR) of the perturbed gradients. Specifically, we find that the SNR increases linearly with rr, implying that clients' learning rates must be dynamically scaled with their adaptation ranks for higher utility. Building on these foundations, we introduce SPRA-LoRA (Stochastic Projection Rank-Aware LoRA), a federated rank-aware fine-tuning strategy that utilizes frozen, resampled A\mathbf{A} matrices and rank-dependent learning rates for clients. We also prove its convergence with heterogeneous client resources. Our experiments across benchmark datasets demonstrate that SPRA-LoRA consistently outperforms state-of-the-art baselines with half the overhead on clients.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-10 06:58 · 最新观测版本

Stochastic Projections and Rank-Aware Learning Rates for Federated LoRA

Fine-tuning large-scale foundation models across resource-constrained, distributed clients presents significant computational and communication challenges. While merging Low-Rank Adaptation (LoRA) with Federated Learning (FL) enables rank-based flexibility, the interdependence of the adaptation matrices (A\mathbf{A} and B\mathbf{B}) often complicates optimization. In this work, we theoretically demonstrate that LoRA fine-tuning with Gaussian initialization and a frozen A\mathbf{A} matrix acts as a stochastic approximation of full fine-tuning, where batch gradients are subject to a random, rank-dependent perturbation. Motivated by this insight, we propose freezing and periodically resampling A\mathbf{A} matrices at the client level. This strategy decouples the A\mathbf{A} and B\mathbf{B} gradients, diminishes LoRA low-rank constraints and reduces both computational and uplink communication overheads by 50\%, allowing for the reallocation of resources toward higher adaptation ranks. Furthermore, we show that in this frozen-A\mathbf{A} regime, the adaptation rank rr directly governs the signal-to-noise ratio (SNR) of the perturbed gradients. Specifically, we find that the SNR increases linearly with rr, implying that clients' learning rates must be dynamically scaled with their adaptation ranks for higher utility. Building on these foundations, we introduce SPRA-LoRA (Stochastic Projection Rank-Aware LoRA), a federated rank-aware fine-tuning strategy that utilizes frozen, resampled A\mathbf{A} matrices and rank-dependent learning rates for clients. We also prove its convergence with heterogeneous client resources. Our experiments across benchmark datasets demonstrate that SPRA-LoRA consistently outperforms state-of-the-art baselines with half the overhead on clients.

查看此版本解读 →查看此版本原文 ↗