Improving the Sample Efficiency of Prompt Tuning with Domain Adaptation

2022-10-06 · Xu Guo, Boyang Li, Han Yu

Prompt tuning, or the conditioning of a frozen pretrained language model (PLM) with soft prompts learned from data, has demonstrated impressive performance on a wide range of NLP tasks. However, prompt tuning requires a large training dataset to be effective and is outperformed by finetuning the entire PLM in data-scarce regimes. Previous work (Gu et al., 2022, Vu et al., 2022) proposed to transfer soft prompts pretrained on the source domain to the target domain. In this paper, we explore domain adaptation for prompt tuning, a problem setting where unlabeled data from the target domain are available during pretraining. We propose bOosting Prompt TunIng with doMain Adaptation (OPTIMA), which regularizes the decision boundary to be smooth around regions where source and target data distributions are similar. Extensive experiments demonstrate that OPTIMA significantly enhances the transferability and sample-efficiency of prompt tuning compared to strong baselines. Moreover, in few-shot settings, OPTIMA exceeds full-model tuning by a large margin.

📄 PDF Abstract BibTeX arXiv:2210.02952

Code (1)

guoxuxu/soft-prompt-transfer 공식 구현 pytorch

Tasks

Domain AdaptationLanguage ModelingLanguage Modelling

pMoE: Prompting Diverse Experts Together Wins More in Visual Adaptation

2026-02-26 · Shentong Mo, Xufang Luo, Dongsheng Li arxiv

Parameter-efficient fine-tuning has demonstrated promising results across various visual adaptation tasks, such as classification and segmentation. Typically, prompt tuning techniques have harnessed knowledge from a sing…

parameter-efficient fine-tuning Computational Efficiency

Visual Prompt Tuning for Test-time Domain Adaptation

2022-10-10 · Yunhe Gao, Xingjian Shi, Yi Zhu, Hao Wang 외

Models should be able to adapt to unseen data during test-time to avoid performance drops caused by inevitable distribution shifts in real-world deployment scenarios. In this work, we tackle the practical yet challenging…

Domain Adaptation Test-time Adaptation Unsupervised Domain Adaptation Visual Prompt Tuning

Prompt Tuning for Audio Deepfake Detection: Computationally Efficient Test-time Domain Adaptation with Limited Target Dataset

2024-10-13 · Hideyuki Oiso, Yuto Matsunaga, Kazuya Kakizaki, Taiki Miyagawa

We study test-time domain adaptation for audio deepfake detection (ADD), addressing three challenges: (i) source-target domain gaps, (ii) limited target dataset size, and (iii) high computational costs. We propose an ADD…

Audio Deepfake Detection Computational Efficiency DeepFake Detection Domain Adaptation+1

Dynamic Prompt Allocation and Tuning for Continual Test-Time Adaptation

2024-12-12 · Chaoran Cui, Yongrui Zhen, Shuai Gong, Chunyun Zhang 외

Continual test-time adaptation (CTTA) has recently emerged to adapt a pre-trained source model to continuously evolving target distributions, which accommodates the dynamic nature of real-world environments. To mitigate …

Test-time Adaptation

MetaTPT: Meta Test-time Prompt Tuning for Vision-Language Models

2025-12-13 · Yuqing Lei, Yingjun Du, Yawen Huang, Xiantong Zhen 외 arxiv

Vision-language models (VLMs) such as CLIP exhibit strong zero-shot generalization but remain sensitive to domain shifts at test time. Test-time prompt tuning (TPT) mitigates this issue by adapting prompts with fixed aug…

Zero-shot Generalization Domain Generalization Test-time Adaptation