Delta-LoRA: Fine-Tuning High-Rank Parameters with the Delta of Low-Rank Matrices
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Parameter-Efficient Fine-Tuning via Circular Convolution
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-tuningParameter-Efficient Fine-Tuning with Discrete Fourier Transform
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+1SBoRA: Low-Rank Adaptation with Regional Weight Updates
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-tuningA Single Linear Layer Yields Task-Adapted Low-Rank Matrices
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-tuningEfficient Modular Learning through Naive LoRA Summation: Leveraging Orthogonality in High-Dimensional Models
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