arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.08271cs.CLcs.AI
收藏

基于高效适配器的前沿Transformer模型微调的对比分析

Comparative Analysis of Efficient Adapter-Based Fine-Tuning of State-of-the-Art Transformer Models

Saad Mashkoor Siddiqui, Mohammad Ali Sheikh, Muhammad Aleem, Kajol R Singh

AI总结:

本研究对比了三种Transformer模型结合九种前沿适配器架构与传统微调在分类任务上的表现,发现适配器能用更少训练时间达到相当或更优性能,为NLP应用中适配器的选型与部署提供参考。

摘要:

本研究探究了多种适配器架构在SuperGLUE基准的监督二分类任务,以及Kaggle的监督多类新闻分类任务上的效果。具体而言,我们对比了DistilBERT、ELECTRA和BART这三个Transformer模型,分别使用传统微调方法与九种前沿(SoTA)适配器架构的分类性能和时间复杂度。分析表明不同适配器架构存在性能差异,凸显其仅用微调训练时间的一小部分,就能达到与微调相当甚至更优性能的能力。在新分类任务上也观察到了相似结果,进一步支撑了我们的发现,证明适配器是微调的高效且灵活的替代方案。本研究为在各类自然语言处理(NLP)应用中选择和部署适配器提供了宝贵见解与指导。

英文摘要:

In this work, we investigate the efficacy of various adapter architectures on supervised binary classification tasks from the SuperGLUE benchmark as well as a supervised multi-class news category classification task from Kaggle. Specifically, we compare classification performance and time complexity of three transformer models, namely DistilBERT, ELECTRA, and BART, using conventional fine-tuning as well as nine state-of-the-art (SoTA) adapter architectures. Our analysis reveals performance differences across adapter architectures, highlighting their ability to achieve comparable or better performance relative to fine-tuning at a fraction of the training time. Similar results are observed on the new classification task, further supporting our findings and demonstrating adapters as efficient and flexible alternatives to fine-tuning. This study provides valuable insights and guidelines for selecting and implementing adapters in diverse natural language processing (NLP) applications.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑