SVFit: Parameter-Efficient Fine-Tuning of Large Pre-Trained Models Using Singular Values
This addresses memory challenges in fine-tuning large pre-trained models for NLP and computer vision, offering a more efficient solution for resource-constrained environments, though it is incremental as it builds on existing PEFT methods.
The paper tackles the inefficiency and suboptimal performance of parameter-efficient fine-tuning methods like LoRA by proposing SVFit, which uses singular value decomposition to initialize low-rank matrices with critical singular values as trainable parameters, resulting in outperforming LoRA with 16 times fewer trainable parameters across various tasks.
Large pre-trained models (LPMs) have demonstrated exceptional performance in diverse natural language processing and computer vision tasks. However, fully fine-tuning these models poses substantial memory challenges, particularly in resource-constrained environments. Parameter-efficient fine-tuning (PEFT) methods, such as LoRA, mitigate this issue by adjusting only a small subset of parameters. Nevertheless, these methods typically employ random initialization for low-rank matrices, which can lead to inefficiencies in gradient descent and diminished generalizability due to suboptimal starting points. To address these limitations, we propose SVFit, a novel PEFT approach that leverages singular value decomposition (SVD) to initialize low-rank matrices using critical singular values as trainable parameters. Specifically, SVFit performs SVD on the pre-trained weight matrix to obtain the best rank-r approximation matrix, emphasizing the most critical singular values that capture over 99% of the matrix's information. These top-r singular values are then used as trainable parameters to scale the fundamental subspaces of the matrix, facilitating rapid domain adaptation. Extensive experiments across various pre-trained models in natural language understanding, text-to-image generation, and image classification tasks reveal that SVFit outperforms LoRA while requiring 16 times fewer trainable parameters.