X-PEFT: eXtremely Parameter-Efficient Fine-Tuning for Extreme Multi-Profile Scenarios

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kwak, Namju, Kim, Taesup
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911766728933376
author Kwak, Namju
Kim, Taesup
author_facet Kwak, Namju
Kim, Taesup
contents Parameter-efficient fine-tuning (PEFT) techniques, such as adapter tuning, aim to fine-tune a pre-trained language model (PLM) using a minimal number of parameters for a specific task or profile. Although adapter tuning provides increased parameter efficiency compared to full-model fine-tuning, it introduces a small set of additional parameters attached to a PLM for each profile. This can become problematic in practical applications with multiple profiles, particularly when a significant increase in the number of profiles linearly boosts the total number of additional parameters. To mitigate this issue, we introduce X-PEFT, a novel PEFT method that leverages a multitude of given adapters by fine-tuning an extremely small set of compact tensors for a new profile, which serve as binary masks to adaptively select the given adapters. To efficiently validate our proposed method, we implement it using a large number of trained or untrained (random) adapters. We evaluate the performance of X-PEFT through LaMP and GLUE tasks and demonstrate that it either matches or surpasses the effectiveness of conventional adapter tuning, despite reducing the memory requirements per profile by a factor of 10,000 compared to it.
format Preprint
id arxiv_https___arxiv_org_abs_2401_16137
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle X-PEFT: eXtremely Parameter-Efficient Fine-Tuning for Extreme Multi-Profile Scenarios
Kwak, Namju
Kim, Taesup
Machine Learning
Artificial Intelligence
Computation and Language
Parameter-efficient fine-tuning (PEFT) techniques, such as adapter tuning, aim to fine-tune a pre-trained language model (PLM) using a minimal number of parameters for a specific task or profile. Although adapter tuning provides increased parameter efficiency compared to full-model fine-tuning, it introduces a small set of additional parameters attached to a PLM for each profile. This can become problematic in practical applications with multiple profiles, particularly when a significant increase in the number of profiles linearly boosts the total number of additional parameters. To mitigate this issue, we introduce X-PEFT, a novel PEFT method that leverages a multitude of given adapters by fine-tuning an extremely small set of compact tensors for a new profile, which serve as binary masks to adaptively select the given adapters. To efficiently validate our proposed method, we implement it using a large number of trained or untrained (random) adapters. We evaluate the performance of X-PEFT through LaMP and GLUE tasks and demonstrate that it either matches or surpasses the effectiveness of conventional adapter tuning, despite reducing the memory requirements per profile by a factor of 10,000 compared to it.
title X-PEFT: eXtremely Parameter-Efficient Fine-Tuning for Extreme Multi-Profile Scenarios
topic Machine Learning
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2401.16137