paper-with-me

Papers

The Power of Scale for Parameter-Efficient Prompt Tuning

2021-04-18 · EMNLP 2021 11 · Brian Lester, Rami Al-Rfou, Noah Constant

In this work, we explore "prompt tuning", a simple yet effective mechanism for learning "soft prompts" to condition frozen language models to perform specific downstream tasks. Unlike the discrete text prompts used by GPT-3, soft prompts are learned through backpropagation and can be tuned to incorporate signal from any number of labeled examples. Our end-to-end learned approach outperforms GPT-3's "few-shot" learning by a large margin. More remarkably, through ablations on model size using T5, we show that prompt tuning becomes more competitive with scale: as models exceed billions of parameters, our method "closes the gap" and matches the strong performance of model tuning (where all model weights are tuned). This finding is especially relevant in that large models are costly to share and serve, and the ability to reuse one frozen model for multiple downstream tasks can ease this burden. Our method can be seen as a simplification of the recently proposed "prefix tuning" of Li and Liang (2021), and we provide a comparison to this and other similar approaches. Finally, we show that conditioning a frozen model with soft prompts confers benefits in robustness to domain transfer, as compared to full model tuning.

📄 PDF Abstract BibTeX arXiv:2104.08691

Code (12)

google-research/prompt-tuning 공식 구현 jax
RossNordby/SoftPromptsForEvaluation pytorch
VE-FORBRYDERNE/mtj-softtuner jax
Zeng-WH/Prompt-Tuning pytorch
arazd/ProgressivePrompts pytorch
corolla-johnson/mkultra pytorch
exelents/soft-prompt-tuning pytorch
google-deepmind/thunnini jax
hellokevin07/elastictrainer tf
kipgparker/soft-prompt-tuning pytorch
mkshing/Prompt-Tuning pytorch
zhanglab-aim/lingo pytorch

Tasks

Few-Shot Learning

Methods 이 논문이 사용한 방법론

Gated Linear Unit A Gated Linear Unit, or GLU computes: $$ \mathrm{GLU}(a, b) = a \otimes \sigma(b) $$ It is used in natural language processing architectures, for example the Gated CNN,…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Adafactor Adafactor is a stochastic optimization method based on Adam that reduces memory usage while retaining the empirical benefits of…
Inverse Square Root Schedule Inverse Square Root is a learning rate schedule 1 / $\sqrt{\max\left(n, k\right)}$ where $n$ is the current training iteration and $k$ is the number of warm-up steps. This…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

VoP: Text-Video Co-operative Prompt Tuning for Cross-Modal Retrieval

2022-11-23 · CVPR 2023 1 · Siteng Huang, Biao Gong, Yulin Pan, Jianwen Jiang 외

Many recent studies leverage the pre-trained CLIP for text-video cross-modal retrieval by tuning the backbone with additional heavy modules, which not only brings huge computational burdens with much more parameters, but…

Cross-Modal RetrievalRetrievalVideo Retrieval

XPrompt: Exploring the Extreme of Prompt Tuning

2022-10-10 · Fang Ma, Chen Zhang, Lei Ren, Jingang Wang 외

Prompt tuning learns soft prompts to condition frozen Pre-trained Language Models (PLMs) for performing downstream tasks in a parameter-efficient manner. While prompt tuning has gradually reached the performance level of…

DMPT: Decoupled Modality-aware Prompt Tuning for Multi-modal Object Re-identification

2025-04-15 · Minghui Lin, Shu Wang, Xiang Wang, Jianhua Tang 외

Current multi-modal object re-identification approaches based on large-scale pre-trained backbones (i.e., ViT) have displayed remarkable progress and achieved excellent performance. However, these methods usually adopt t…

Query Efficient Black-Box Visual Prompting with Subspace Learning

2025-01-01 · CVPR 2025 1 · Zhaogeng Liu, Haozhen Zhang, Hualin Zhang, Xingchen Li 외

Visual Prompt Learning (VPL) has emerged as a powerful strategy for harnessing the capabilities of large-scale pre-trained models (PTMs) to tackle specific downstream tasks. However, the opaque nature of PTMs in many…

Prompt LearningVisual Prompting

ULPT: Prompt Tuning with Ultra-Low-Dimensional Optimization

2025-02-06 · Zijun Wu, Yongchang Hao, Lili Mou

Large language models achieve state-of-the-art performance but are costly to fine-tune due to their size. Parameter-efficient fine-tuning methods, such as prompt tuning, address this by reducing trainable parameters whil…

parameter-efficient fine-tuning