paper-with-me

홈 › Papers

Parameter-Efficient Fine-Tuning with Column Space Projection

2025-05-26 · Junseo Hwang, Wonguk Cho, Taesup Kim

Fine-tuning large language models (LLMs) with minimal computational overhead is essential for efficiently adapting them to downstream tasks under resource constraints. Parameter-efficient fine-tuning (PEFT) methods, such as Low-Rank Adaptation (LoRA), facilitate this by updating only a small subset of parameters. However, recent studies show that LoRA diverges from full fine-tuning (Full FT) in its learning behavior, particularly in terms of spectral properties. Motivated by these findings, we propose PiCa, the first theoretically grounded PEFT method based on the spectral properties of fine-tuned weights. PiCa projects gradients onto the low-rank column subspace of pre-trained weights and exhibits learning patterns more closely aligned with Full FT. Furthermore, we show that combining PiCa with weight sharing drastically reduces the number of trainable parameters without compromising performance, enabling to achieve superior performance than LoRA using 13x fewer trainable parameters. Extensive experiments demonstrate PiCa achieves the state-of-the-art performance compared to existing PEFT methods.

📄 PDF Abstract BibTeX arXiv:2505.20211

Code (0)

등록된 구현이 없습니다.

Tasks

parameter-efficient fine-tuning

Similar Papers 제목 키워드 기반

Efficient Adaptation of Pre-trained Vision Transformer underpinned by Approximately Orthogonal Fine-Tuning Strategy

2025-07-17 · Yiting Yang, Hao Luo, Yuan Sun, Qingsen Yan 외

A prevalent approach in Parameter-Efficient Fine-Tuning (PEFT) of pre-trained Vision Transformers (ViT) involves freezing the majority of the backbone parameters and solely learning low-rank adaptation weight matrices to…

image-classificationImage Classificationparameter-efficient fine-tuning

Farthest sampling segmentation of triangulated surfaces

2020-12-01 · Victoria Hernández-Mederos, Dimas Martínez, Jorge Estrada-Sarlabous, Valia Guerra-Ones

In this paper we introduce Farthest Sampling Segmentation (FSS), a new method for segmentation of triangulated surfaces, which consists of two fundamental steps: the computation of a submatrix $W^k$ of the affinity matri…

ClusteringSegmentation

UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter-Efficient Fine-Tuning of Large Models

2025-05-26 · Xueyan Zhang, Jinman Zhao, Zhifei Yang, Yibo Zhong 외

This paper introduces Uniform Orthogonal Reinitialization Adaptation (UORA), a novel parameter-efficient fine-tuning (PEFT) approach for Large Language Models (LLMs). UORA achieves state-of-the-art performance and parame…

image-classificationImage Classificationparameter-efficient fine-tuning

D2-LoRA: A Synergistic Approach to Differential and Directional Low-Rank Adaptation

2026-02-16 · Nozomu Fujisawa, Masaaki Kondo arxiv

We systematically investigate the parameter-efficient fine-tuning design space under practical data and compute constraints, and propose D2-LoRA. D2-LoRA achieves 76.4 percent average accuracy across eight question answe…

parameter-efficient fine-tuningReading ComprehensionQuestion Answering

FoRA: Fisher-orthogonal Rank Adaptation for Parameter-Efficient Fine-Tuning

2026-05-28 · Juneyoung Park, Seongbae Lee, Han-Sang Lee, Kyuho Lee 외 arxiv

Parameter-efficient fine-tuning(PEFT) has largely focused on LoRA and its accuracy-oriented variants, leaving the original goal of reducing trainable parameters has receivedcomparatively little attention. We introduce Fo…

parameter-efficient fine-tuning