Research

Paper

AI LLM February 23, 2026

Rethinking LoRA for Privacy-Preserving Federated Learning in Large Models

Authors

Jin Liu, Yinbin Miao, Ning Xi, Junkang Liu

Abstract

Fine-tuning large vision models (LVMs) and large language models (LLMs) under differentially private federated learning (DPFL) is hindered by a fundamental privacy-utility trade-off. Low-Rank Adaptation (LoRA), a promising parameter-efficient fine-tuning (PEFT) method, reduces computational and communication costs by introducing two trainable low-rank matrices while freezing pre-trained weights. However, directly applying LoRA in DPFL settings leads to performance degradation, especially in LVMs. Our analysis reveals three previously underexplored challenges: (1) gradient coupling caused by the simultaneous update of two asymmetric low-rank matrices, (2) compounded noise amplification under differential privacy, and (3) sharpness of the global aggregated model in the parameter space. To address these issues, we propose LA-LoRA (\textbf{L}ocal \textbf{A}lternating \textbf{LoRA}), a novel approach that decouples gradient interactions and aligns update directions across clients to enhance robustness under stringent privacy constraints. Theoretically, LA-LoRA strengthens convergence guarantees in noisy federated environments. Extensive experiments demonstrate that LA-LoRA achieves state-of-the-art (SOTA) performance on Swin Transformer and RoBERTa models, showcasing robustness to DP noise and broad applicability across both LVMs and LLMs. For example, when fine-tuning the Swin-B model on the Tiny-ImageNet dataset under a strict privacy budget ($ε= 1$), LA-LoRA outperforms the best baseline, RoLoRA, by 16.83\% in test accuracy. Code is provided in \repolink.

Metadata

arXiv ID: 2602.19926
Provider: ARXIV
Primary Category: cs.LG
Published: 2026-02-23
Fetched: 2026-02-24 04:38

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.19926v1</id>\n    <title>Rethinking LoRA for Privacy-Preserving Federated Learning in Large Models</title>\n    <updated>2026-02-23T15:05:28Z</updated>\n    <link href='https://arxiv.org/abs/2602.19926v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.19926v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Fine-tuning large vision models (LVMs) and large language models (LLMs) under differentially private federated learning (DPFL) is hindered by a fundamental privacy-utility trade-off. Low-Rank Adaptation (LoRA), a promising parameter-efficient fine-tuning (PEFT) method, reduces computational and communication costs by introducing two trainable low-rank matrices while freezing pre-trained weights. However, directly applying LoRA in DPFL settings leads to performance degradation, especially in LVMs. Our analysis reveals three previously underexplored challenges: (1) gradient coupling caused by the simultaneous update of two asymmetric low-rank matrices, (2) compounded noise amplification under differential privacy, and (3) sharpness of the global aggregated model in the parameter space. To address these issues, we propose LA-LoRA (\\textbf{L}ocal \\textbf{A}lternating \\textbf{LoRA}), a novel approach that decouples gradient interactions and aligns update directions across clients to enhance robustness under stringent privacy constraints. Theoretically, LA-LoRA strengthens convergence guarantees in noisy federated environments. Extensive experiments demonstrate that LA-LoRA achieves state-of-the-art (SOTA) performance on Swin Transformer and RoBERTa models, showcasing robustness to DP noise and broad applicability across both LVMs and LLMs. For example, when fine-tuning the Swin-B model on the Tiny-ImageNet dataset under a strict privacy budget ($ε= 1$), LA-LoRA outperforms the best baseline, RoLoRA, by 16.83\\% in test accuracy. Code is provided in \\repolink.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-02-23T15:05:28Z</published>\n    <arxiv:primary_category term='cs.LG'/>\n    <author>\n      <name>Jin Liu</name>\n    </author>\n    <author>\n      <name>Yinbin Miao</name>\n    </author>\n    <author>\n      <name>Ning Xi</name>\n    </author>\n    <author>\n      <name>Junkang Liu</name>\n    </author>\n  </entry>"
}