cs.LGNov 18, 2026

Same Rank, Different Needs: Rethinking LoRA Redistribution in Federated Learning

Authors: Jinqian Chen, Jihua Zhu, Chang Liu

Organizations: School of Software Engineering, Xi’an Jiaotong University

Abstract

Federated low-rank adaptation (LoRA) enables clients with different resource budgets to collaboratively fine-tune foundation models. To distribute an aggregated update within each client's rank budget, existing methods commonly retain its leading singular directions. However, directions that best reconstruct the update matrix need not best preserve its responses on a particular client's inputs: a lower-energy direction may matter more to that recipient. We formalize this mismatch and show that matrix-optimal truncation can incur arbitrarily larger response error than another readout of the same rank. Motivated by this result, we propose Receiver-Aware Subspace Adaptation (RASA), a plug-in framework for receiver-aware knowledge transfer. RASA uses compact diagonal input second moments to perform uncentered PCA of receiver-weighted update responses. The resulting readout is globally optimal for the rank-constrained receiver objective and preserves at least as much response energy as spectral truncation under the diagonal metric. RASA also introduces spectral-reference aggregation, which removes the personalized initialization offset while retaining the locally learned increment. Experiments on DomainNet-100, NICO++, GLUE, and SuperNI demonstrate RASA's effectiveness across methods under resource, task, and data heterogeneity. In particular, RASA improves DomainNet-100 accuracy by 3.23 percentage points with FlexLoRA and achieves gains of up to 8.33 ROUGE-L points on seen SuperNI tasks and 4.37 on unseen tasks with modest overhead.

Figures & tables

Explore similar work

Aug 10, 2026

Rethinking Factor Sharing in Federated LoRA: A Rank-Aware Adaptive Approach

Low-rank adaptation (LoRA) represents large language model (LLM) updates with two compact matrix factors, i.e., AA and BB, providing an efficient way to fine-tune large models in federated learning paradigm. Inspired by the asymmetric roles of the LoRA factors, we study whether AA should be shared across clients while BB remains client-specific (Share-A/Local-B), or whether BB should instead be shared while AA remains client-specific (Share-B/Local-A). With a least-squares surrogate, we reveal that Share-A/Local-B requires the client-specific LoRA update matrices to use a common rank-rr input-side space, whereas Share-B/Local-A requires a common rank-rr output-side space. The two strategies therefore incur different projection residuals, indicating that the preferred strategy is the one with the smaller aggregate residual across clients. With this insight, we propose Federated Adaptive Factor Sharing Low-Rank Adaptation (FedAS-LoRA), which selects the sharing side before training to enhance fine-tuning performance. To enable adaptive factor selection before training, we design a Rank-Aware Shared-Subspace Sufficiency (RSS) metric, which effectively assesses whether a shared rank-rr input subspace is sufficient for the local data distributions using representations extracted from a frozen LLM backbone. Experiments across different tasks, data distributions, LoRA ranks, and participation settings confirm the effectiveness of RSS and the superior performance of FedAS-LoRA.
Nov 9, 2026

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.
Jun 21, 2026

Subspace-Constrained Federated Learning with Low-Rank Adaptation

Federated low-rank adaptation methods are attractive for fine-tuning large models under communication and privacy constraints, but heterogeneous client data can induce geometric misalignment between local low-rank updates. We study whether this subspace misalignment leads to destructive aggregation and slower convergence in LoRA-based federated learning. We propose a subspace-regularized federated LoRA objective that encourages local client updates to remain close to a shared global reference subspace. We present a complete empirical evaluation on two pretrained models, RoBERTa-large and SmolLM-360M, over HellaSwag in a non-IID 10-client federated setting, across 3 random seeds (42, 43, 44), yielding 24 total experimental runs (4 methods x 3 seeds x 2 models). On RoBERTa-large, Subspace-Reg achieves the strongest mean best accuracy (0.454 +/- 0.023), mean final accuracy (0.429 +/- 0.011), and lowest final loss (1.363) across all three seeds, outperforming FedAvg, SVD redistribution, and FedSVD baselines by a large margin. On SmolLM-360M, FedAvg leads on accuracy, revealing that accuracy gains are model-dependent. Crucially, Subspace-Reg achieves near-perfect basis overlap, approximately 0.9999, on both models and across all seeds, versus 0.958 to 0.991 for all baselines, providing robust support for the geometric alignment hypothesis. The code is publicly available at https://github.com/sadia-sigma-lab/Subspace-Constrained-Federated-learning-with-Lora.