Prompt Tuning Strikes Back: Customizing Foundation Models with Low-Rank Prompt Adaptation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Jain, Abhinav, Chaudhuri, Swarat, Reps, Thomas, Jermaine, Chris
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916464031694848
author Jain, Abhinav
Chaudhuri, Swarat
Reps, Thomas
Jermaine, Chris
author_facet Jain, Abhinav
Chaudhuri, Swarat
Reps, Thomas
Jermaine, Chris
contents Parameter-Efficient Fine-Tuning (PEFT) has become the standard for customising Foundation Models (FMs) to user-specific downstream tasks. However, typical PEFT methods require storing multiple task-specific adapters, creating scalability issues as these adapters must be housed and run at the FM server. Traditional prompt tuning offers a potential solution by customising them through task-specific input prefixes, but it under-performs compared to other PEFT methods like LoRA. To address this gap, we propose Low-Rank Prompt Adaptation (LoPA), a prompt-tuning-based approach that performs on par with state-of-the-art PEFT methods and full fine-tuning while being more parameter-efficient and not requiring a server-based adapter. LoPA generates soft prompts by balancing between sharing task-specific information across instances and customization for each instance. It uses a low-rank decomposition of the soft-prompt component encoded for each instance to achieve parameter efficiency. We provide a comprehensive evaluation on multiple natural language understanding and code generation and understanding tasks across a wide range of foundation models with varying sizes.
format Preprint
id arxiv_https___arxiv_org_abs_2405_15282
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Prompt Tuning Strikes Back: Customizing Foundation Models with Low-Rank Prompt Adaptation
Jain, Abhinav
Chaudhuri, Swarat
Reps, Thomas
Jermaine, Chris
Machine Learning
Artificial Intelligence
Parameter-Efficient Fine-Tuning (PEFT) has become the standard for customising Foundation Models (FMs) to user-specific downstream tasks. However, typical PEFT methods require storing multiple task-specific adapters, creating scalability issues as these adapters must be housed and run at the FM server. Traditional prompt tuning offers a potential solution by customising them through task-specific input prefixes, but it under-performs compared to other PEFT methods like LoRA. To address this gap, we propose Low-Rank Prompt Adaptation (LoPA), a prompt-tuning-based approach that performs on par with state-of-the-art PEFT methods and full fine-tuning while being more parameter-efficient and not requiring a server-based adapter. LoPA generates soft prompts by balancing between sharing task-specific information across instances and customization for each instance. It uses a low-rank decomposition of the soft-prompt component encoded for each instance to achieve parameter efficiency. We provide a comprehensive evaluation on multiple natural language understanding and code generation and understanding tasks across a wide range of foundation models with varying sizes.
title Prompt Tuning Strikes Back: Customizing Foundation Models with Low-Rank Prompt Adaptation
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2405.15282