paper-with-me

홈 › Papers

Delta-LoRA: Fine-Tuning High-Rank Parameters with the Delta of Low-Rank Matrices

2023-09-05 · Bojia Zi, Xianbiao Qi, Lingzhi Wang, Jianan Wang, Kam-Fai Wong, Lei Zhang

In this paper, we present Delta-LoRA, which is a novel parameter-efficient approach to fine-tune large language models (LLMs). In contrast to LoRA and other low-rank adaptation methods such as AdaLoRA, Delta-LoRA not only updates the low-rank matrices $\bA$ and $\bB$, but also propagate the learning to the pre-trained weights $\bW$ via updates utilizing the delta of the product of two low-rank matrices ($\bA^{(t+1)}\bB^{(t+1)} - \bA^{(t)}\bB^{(t)}$). Such a strategy effectively addresses the limitation that the incremental update of low-rank matrices is inadequate for learning representations capable for downstream tasks. Moreover, as the update of $\bW$ does not need to compute the gradients of $\bW$ and store their momentums, Delta-LoRA shares comparable memory requirements and computational costs with LoRA. Extensive experiments show that Delta-LoRA significantly outperforms existing low-rank adaptation methods. We further support these results with comprehensive analyses that underscore the effectiveness of Delta-LoRA.

📄 PDF Abstract BibTeX arXiv:2309.02411

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Parameter-Efficient Fine-Tuning via Circular Convolution

2024-07-27 · Aochuan Chen, Jiashun Cheng, Zijing Liu, Ziqi Gao 외

Low-Rank Adaptation (LoRA) has gained popularity for fine-tuning large foundation models, leveraging low-rank matrices $\mathbf{A}$ and $\mathbf{B}$ to represent weight changes (i.e., $\Delta \mathbf{W} = \mathbf{B} \mat…

parameter-efficient fine-tuning

Parameter-Efficient Fine-Tuning with Discrete Fourier Transform

2024-05-05 · Ziqi Gao, Qichao Wang, Aochuan Chen, Zijing Liu 외

Low-rank adaptation~(LoRA) has recently gained much interest in fine-tuning foundation models. It effectively reduces the number of trainable parameters by incorporating low-rank matrices $A$ and $B$ to represent the wei…

image-classificationImage ClassificationNatural Language Understandingparameter-efficient fine-tuning+1

SBoRA: Low-Rank Adaptation with Regional Weight Updates

2024-07-07 · Lai-Man Po, Yuyang Liu, Haoxuan Wu, Tianqi Zhang 외

This paper introduces Standard Basis LoRA (SBoRA), a novel parameter-efficient fine-tuning approach for Large Language Models that builds upon the pioneering works of Low-Rank Adaptation (LoRA) and Orthogonal Adaptation.…

Arithmetic Reasoningparameter-efficient fine-tuning

A Single Linear Layer Yields Task-Adapted Low-Rank Matrices

2024-03-22 · Hwichan Kim, Shota Sasaki, Sho Hoshino, Ukyo Honda

Low-Rank Adaptation (LoRA) is a widely used Parameter-Efficient Fine-Tuning (PEFT) method that updates an initial weight matrix $W_0$ with a delta matrix $\Delta W$ consisted by two low-rank matrices $A$ and $B$. A previ…

parameter-efficient fine-tuning

Efficient Modular Learning through Naive LoRA Summation: Leveraging Orthogonality in High-Dimensional Models

2025-08-16 · Zhanhao Cao, Clement Truong, Andrew Lizarraga arxiv

Recent advances in large language models are driven by scale, while parameter-efficient fine-tuning (PEFT) enables updating only a small fraction of parameters. Low-Rank Adaptation (LoRA) stores parameter deltas as the p…

parameter-efficient fine-tuning