paper-with-me

Papers

Sparse Structure Search for Parameter-Efficient Tuning

2022-06-15 · Shengding Hu, Zhen Zhang, Ning Ding, Yadao Wang, Yasheng Wang, Zhiyuan Liu, Maosong Sun

Adapting large pre-trained models (PTMs) through fine-tuning imposes prohibitive computational and storage burdens. Recent studies of parameter-efficient tuning (PET) find that only optimizing a small portion of parameters conditioned on PTMs could yield on-par performance compared to conventional fine-tuning. Generally, PET methods exquisitely design parameter-efficient modules (PET modules) which could be applied to arbitrary fine-grained positions inside PTMs. However, the effectiveness of these fine-grained positions largely relies on sophisticated manual designation, thereby usually producing sub-optimal results. In contrast to the manual designation, we explore constructing PET modules in an automatic manner. We automatically \textbf{S}earch for the \textbf{S}parse \textbf{S}tructure of \textbf{P}arameter-\textbf{E}fficient \textbf{T}uning (S$^3$PET). Based on a unified framework of various PET methods, S$^3$PET conducts the differentiable PET structure search through bi-level optimization and proposes shifted global sigmoid method to explicitly control the number of trainable parameters. Extensive experiments show that S$^3$PET surpasses manual and random structures with less trainable parameters. The searched structures preserve more than 99\% fine-tuning performance with 0.01\% trainable parameters. Moreover, the advantage of S$^3$PET is amplified with extremely low trainable parameters budgets (0.0009\%$\sim$0.01\%). The searched structures are transferable and explainable, providing suggestions and guidance for the future design of PET methods.

📄 PDF Abstract BibTeX arXiv:2206.07382

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

S2FT: Parameter-Efficient Fine-Tuning in Sparse Spectrum Domain

2026-05-09 · Baoquan Zhang, Zhehao Yu, Lisai Zhang, Kenghong Lin 외 arxiv

Parameter Efficient Fine-Tuning (PEFT) is a key technique for adapting a large pretrained model to downstream tasks by fine-tuning only a small number of parameters. Recent methods based on Fourier transforms have furthe…

parameter-efficient fine-tuning

Sparse Structure Search for Delta Tuning

2022-11-01 · NIPS 2022 11 · Shengding Hu, Zhen Zhang, Ning Ding, Yadao Wang 외

Adapting large pre-trained models (PTMs) through fine-tuning imposes prohibitive computational and storage burdens. Recent studies of delta tuning (DT), i.e., parameter-efficient tuning, find that only optimizing a smal…

Sensitivity-Aware Efficient Fine-Tuning via Compact Dynamic-Rank Adaptation

2025-01-01 · CVPR 2025 1 · Tianran Chen, Jiarui Chen, Baoquan Zhang, Zhehao Yu 외

Parameter-Efficient Fine-Tuning (PEFT) is a fundamental research problem in computer vision, which aims to tune a few of parameters for efficient storage and adaptation of pre-trained vision models. Recently, sensiti…

parameter-efficient fine-tuningSensitivity

Path Thresholding: Asymptotically Tuning-Free High-Dimensional Sparse Regression

2014-02-23 · Divyanshu Vats, Richard G. Baraniuk

In this paper, we address the challenging problem of selecting tuning parameters for high-dimensional sparse regression. We propose a simple and computationally efficient method, called path thresholding (PaTh), that tra…

Model SelectionregressionVocal Bursts Intensity Prediction

Persistent Homology in Sparse Regression and Its Application to Brain Morphometry

2014-08-31 · Moo. K. Chung, Jamie L. Hanson, Jieping Ye, Richard J. Davidson 외

Sparse systems are usually parameterized by a tuning parameter that determines the sparsity of the system. How to choose the right tuning parameter is a fundamental and difficult problem in learning the sparse system. In…

Brain Morphometryregression