.png){kind=icon}
返回
AutoPEFT : Automatic Configuration Search for Parameter-Efficient Fine-Tuning
.png){kind=icon}
OA
AI
DOI：10.1162/tacl_a_00662.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Large pretrained language models are widely used in downstream NLP tasks via task- specific fine-tuning, but such procedures can be costly. Recently, Parameter-Efficient Fine-Tuning (PEFT) methods have achieved strong task performance while updating much fewer parameters than full model fine-tuning (FFT). However, it is non-trivial to make informed design choices on the PEFT configurations, such as their architecture, the number of tunable parameters, and even the layers in which the PEFT modules are inserted. Consequently, it is highly likely that the current, manually designed configurations are suboptimal in terms of their performance-efficiency trade-off. Inspired by advances in neural architecture search, we propose AutoPEFT for automatic PEFT configuration selection: We first design an expressive configuration search space with multiple representative PEFT modules as building blocks. Using multi-objective Bayesian optimization in a low-cost setup, we then discover a Pareto-optimal set of configurations with strong performance-cost trade-offs across different numbers of parameters that are also highly transferable across different tasks. Empirically, on GLUE and SuperGLUE tasks, we show that AutoPEFT-discovered configurations significantly outperform existing PEFT methods and are on par or better than FFT without incurring substantial training efficiency costs.
期刊
T
IF:
6.9
论文数:
486
被引数:
5.7K
机构
引用论文
.png){kind=icon}
Sodium channel kinetic changes that produce Brugada syndrome or progressive cardiac conduction system disease产生Brugada综合征或进行性心脏传导系统疾病的钠通道动力学变化
PREAI
分享收藏分享收藏The adsorption of monolayer coatings on iron nanoparticles: Mössbauer spectroscopy and XANES results
PREAI
分享收藏
查看更多内容