paper-with-me

Papers

LoRA-Mini : Adaptation Matrices Decomposition and Selective Training

2024-11-24 · Ayush Singh, Rajdeep Aher, Shivank Garg

The rapid advancements in large language models (LLMs) have revolutionized natural language processing, creating an increased need for efficient, task-specific fine-tuning methods. Traditional fine-tuning of LLMs involves updating a large number of parameters, which is computationally expensive and memory-intensive. Low-Rank Adaptation (LoRA) has emerged as a promising solution, enabling parameter-efficient fine-tuning by reducing the number of trainable parameters. However, while LoRA reduces the number of trainable parameters, LoRA modules still create significant storage challenges. We propose LoRA-Mini, an optimized adaptation of LoRA that improves parameter efficiency by splitting low-rank matrices into four parts, with only the two inner matrices being trainable. This approach achieves upto a 20x reduction compared to standard LoRA in the number of trainable parameters while preserving performance levels comparable to standard LoRA, addressing both computational and storage efficiency in LLM fine-tuning.

📄 PDF Abstract BibTeX arXiv:2411.15804

Code (0)

등록된 구현이 없습니다.

Tasks

parameter-efficient fine-tuning

Similar Papers 제목 키워드 기반

QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation

2025-07-07 · Jiahui Yang, Yongjia Ma, Donglin Di, Hao Li 외 arxiv

Existing text-to-image models often rely on parameter fine-tuning techniques such as Low-Rank Adaptation (LoRA) to customize visual attributes. However, when combining multiple LoRA models for content-style fusion tasks,…

LORA-CRAFT: Cross-layer Rank Adaptation via Frozen Tucker Decomposition of Pre-trained Attention Weights

2026-02-19 · Kasun Dewage, Marianna Pensky, Suranadi De Silva, Shankadeep Mondal arxiv

We introduce CRAFT (Cross-layer Rank Adaptation via Frozen Tucker), a parameter-efficient fine-tuning (PEFT) method that applies Tucker tensor decomposition to pre-trained attention weight matrices stacked across transfo…

parameter-efficient fine-tuning

Selective Aggregation for Low-Rank Adaptation in Federated Learning

2024-10-02 · Pengxin Guo, Shuang Zeng, Yanran Wang, Huijie Fan 외

We investigate LoRA in federated learning through the lens of the asymmetry analysis of the learned $A$ and $B$ matrices. In doing so, we uncover that $A$ matrices are responsible for learning general knowledge, while $B…

Federated LearningGeneral KnowledgeNatural Language Understanding

MLAE: Masked LoRA Experts for Visual Parameter-Efficient Fine-Tuning

2024-05-29 · Junjie Wang, Guangjing Yang, Wentao Chen, Huahui Yi 외

In response to the challenges posed by the extensive parameter updates required for full fine-tuning of large-scale pre-trained models, parameter-efficient fine-tuning (PEFT) methods, exemplified by Low-Rank Adaptation (…

parameter-efficient fine-tuning

QR-LoRA: QR-Based Low-Rank Adaptation for Efficient Fine-Tuning of Large Language Models

2025-08-29 · Jessica Liang, Anirudh Bharadwaj arxiv

The growing scale of Large Language Models (LLMs) has necessitated the development of parameter-efficient fine-tuning techniques. Low-Rank Adaptation (LoRA) has emerged as a promising approach, reducing the number of tra…

parameter-efficient fine-tuning