paper-with-me

홈 › Papers

Meta-Learning Hyperparameters for Parameter Efficient Fine-Tuning

2026-03-02 · Zichen Tian, Yaoyao Liu, Qianru Sun arxiv

Training large foundation models from scratch for domain-specific applications is almost impossible due to data limits and long-tailed distributions -- taking remote sensing (RS) as an example. Fine-tuning natural image pre-trained models on RS images is a straightforward solution. To reduce computational costs and improve performance on tail classes, existing methods apply parameter-efficient fine-tuning (PEFT) techniques, such as LoRA and AdaptFormer. However, we observe that fixed hyperparameters -- such as intra-layer positions, layer depth, and scaling factors, can considerably hinder PEFT performance, as fine-tuning on RS images proves highly sensitive to these settings. To address this, we propose MetaPEFT, a method incorporating adaptive scalers that dynamically adjust module influence during fine-tuning. MetaPEFT dynamically adjusts three key factors of PEFT on RS images: module insertion, layer selection, and module-wise learning rates, which collectively control the influence of PEFT modules across the network. We conduct extensive experiments on three transfer-learning scenarios and five datasets in both RS and natural image domains. The results show that MetaPEFT achieves state-of-the-art performance in cross-spectral adaptation, requiring only a small amount of trainable parameters and improving tail-class accuracy significantly.

📄 PDF Abstract BibTeX arXiv:2603.01759

Code (0)

등록된 구현이 없습니다.

Tasks

parameter-efficient fine-tuning

Similar Papers 제목 키워드 기반

From Black-Box Tuning to Guided Optimization via Hyperparameters Interaction Analysis

2025-12-22 · Moncef Garouani, Ayah Barhrhouj arxiv

Hyperparameters tuning is a fundamental, yet computationally expensive, step in optimizing machine learning models. Beyond optimization, understanding the relative importance and interaction of hyperparameters is critica…

Meta-Learning Hyperparameters for Parameter Efficient Fine-Tuning

2025-01-01 · CVPR 2025 1 · Zichen Tian, Yaoyao Liu, Qianru Sun

Training large foundation models from scratch for domain-specific applications is almost impossible due to data limits and long-tailed distributions -- taking remote sensing (RS) as an example. Fine-tuning natural im…

Meta-Learningparameter-efficient fine-tuningTransfer Learning

Quick-Tune: Quickly Learning Which Pretrained Model to Finetune and How

2023-06-06 · Sebastian Pineda Arango, Fabio Ferreira, Arlind Kadra, Frank Hutter 외

With the ever-increasing number of pretrained models, machine learning practitioners are continuously faced with which pretrained model to use, and how to finetune it for a new dataset. In this paper, we propose a method…

Hyperparameter Optimizationimage-classificationImage Classification

Zero-Shot AutoML with Pretrained Models

2022-06-16 · Ekrem Öztürk, Fabio Ferreira, Hadi S. Jomaa, Lars Schmidt-Thieme 외

Given a new dataset D and a low compute budget, how should we choose a pre-trained model to fine-tune to D, and set the fine-tuning hyperparameters without risking overfitting, particularly if D is small? Here, we extend…

AutoMLMeta-Learning

A Metaheuristic-Driven Approach to Fine-Tune Deep Boltzmann Machines

2021-01-14 · Leandro Aparecido Passos, João Paulo Papa

Deep learning techniques, such as Deep Boltzmann Machines (DBMs), have received considerable attention over the past years due to the outstanding results concerning a variable range of domains. One of the main shortcomin…

Image ReconstructionMetaheuristic Optimization