paper-with-me

홈 › Papers

Adaptive Rank Allocation for Federated Parameter-Efficient Fine-Tuning of Language Models

2025-01-24 · Fei Wu, Jia Hu, Geyong Min, Shiqiang Wang

Pre-trained Language Models (PLMs) have demonstrated their superiority and versatility in modern Natural Language Processing (NLP), effectively adapting to various downstream tasks through further fine-tuning. Federated Parameter-Efficient Fine-Tuning (FedPEFT) has emerged as a promising solution to address privacy and efficiency challenges in distributed training for PLMs on resource-constrained local devices. However, our measurements reveal two key limitations of FedPEFT: heterogeneous data across devices leads to significant performance degradation, and a fixed parameter configuration results in communication inefficiency. To overcome these limitations, we propose FedARA, a novel Adaptive Rank Allocation framework for federated parameter-efficient fine-tuning of language models. Specifically, FedARA employs truncated Singular Value Decomposition (SVD) adaptation to enhance similar feature representation across clients, significantly mitigating the adverse effects of data heterogeneity. Subsequently, it utilizes dynamic rank allocation to progressively identify critical ranks, effectively improving communication efficiency. Lastly, it leverages rank-based module pruning to automatically remove inactive modules, steadily reducing local computational cost and memory usage in each federated learning round. Extensive experiments show that FedARA consistently outperforms baselines by an average of 6.95% to 8.49% across various datasets and models under heterogeneous data while significantly improving communication efficiency by 2.40$ \times$. Moreover, experiments on various edge devices demonstrate substantial decreases in total training time and energy consumption by up to 48.90% and 46.95%, respectively.

📄 PDF Abstract BibTeX arXiv:2501.14406

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learningparameter-efficient fine-tuning

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Adaptive LoRA Experts Allocation and Selection for Federated Fine-Tuning

2025-09-18 · Lei Wang, Jieming Bian, Letian Zhang, Jie Xu arxiv

Large Language Models (LLMs) have demonstrated impressive capabilities across various tasks, but fine-tuning them for domain-specific applications often requires substantial domain-specific data that may be distributed a…

parameter-efficient fine-tuningFederated Learning

Efficient Federated Split Learning for Large Language Models over Communication Networks

2025-04-20 · Kai Zhao, Zhaohui Yang

Fine-tuning pre-trained large language models (LLM) in a distributed manner poses significant challenges on resource-constrained edge devices. To address this challenge, we propose FedsLLM, a novel framework that integra…

Federated Learningparameter-efficient fine-tuning

IGU-LoRA: Adaptive Rank Allocation via Integrated Gradients and Uncertainty-Aware Scoring

2026-03-14 · Xuan Cui, Huiyue Li, Run Zeng, Yunfei Zhao 외 arxiv

As large language models (LLMs) scale to billions of parameters, full-parameter fine-tuning becomes compute- and memory-prohibitive. Parameter-efficient fine-tuning (PEFT) mitigates this issue by updating only a small se…

parameter-efficient fine-tuning

Post-Optimization Adaptive Rank Allocation for LoRA

2026-04-30 · Vishnuprasadh Kumaravelu, Sunil Gupta, P. K. Srijith arxiv

Exponential growth in the scale of modern foundation models has led to the widespread adoption of Low-Rank Adaptation (LoRA) as a parameter-efficient fine-tuning technique. However, standard LoRA implementations disregar…

parameter-efficient fine-tuning

Towards Robust and Efficient Federated Low-Rank Adaptation with Heterogeneous Clients

2024-10-30 · Jabin Koo, Minwoo Jang, Jungseul Ok

Federated fine-tuning for Large Language Models (LLMs) faces significant challenges due to the heavy communication overhead of transmitting large model updates. Although Low Rank Adaptation (LoRA) has been proposed as a …

Federated Learning