Bayesian Multi-Task Transfer Learning for Soft Prompt Tuning

Haeju Lee, Minchan Jeong, SeYoung Yun, Kee-Eung Kim
{"title":"Bayesian Multi-Task Transfer Learning for Soft Prompt Tuning","authors":"Haeju Lee, Minchan Jeong, SeYoung Yun, Kee-Eung Kim","doi":"10.18653/v1/2023.findings-emnlp.329","DOIUrl":null,"url":null,"abstract":"Prompt tuning, in which prompts are optimized to adapt large-scale pre-trained language models to downstream tasks instead of fine-tuning the full model parameters, has been shown to be particularly effective when the prompts are trained in a multi-task transfer learning setting. These methods generally involve individually training prompts for each source task and then aggregating them to provide the initialization of the prompt for the target task. However, this approach critically ignores the fact that some of the source tasks could be negatively or positively interfering with each other. We argue that when we extract knowledge from source tasks via training source prompts, we need to consider this correlation among source tasks for better transfer to target tasks. To this end, we propose a Bayesian approach where we work with the posterior distribution of prompts across source tasks. We obtain representative source prompts corresponding to the samples from the posterior utilizing Stein Variational Gradient Descent, which are then aggregated to constitute the initial target prompt. We show extensive experimental results on the standard benchmark NLP tasks, where our Bayesian multi-task transfer learning approach outperforms the state-of-the-art methods in many settings. Furthermore, our approach requires no auxiliary models other than the prompt itself, achieving a high degree of parameter efficiency.","PeriodicalId":505350,"journal":{"name":"Conference on Empirical Methods in Natural Language Processing","volume":"28 6","pages":"4942-4958"},"PeriodicalIF":0.0000,"publicationDate":"2024-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Conference on Empirical Methods in Natural Language Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.18653/v1/2023.findings-emnlp.329","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Prompt tuning, in which prompts are optimized to adapt large-scale pre-trained language models to downstream tasks instead of fine-tuning the full model parameters, has been shown to be particularly effective when the prompts are trained in a multi-task transfer learning setting. These methods generally involve individually training prompts for each source task and then aggregating them to provide the initialization of the prompt for the target task. However, this approach critically ignores the fact that some of the source tasks could be negatively or positively interfering with each other. We argue that when we extract knowledge from source tasks via training source prompts, we need to consider this correlation among source tasks for better transfer to target tasks. To this end, we propose a Bayesian approach where we work with the posterior distribution of prompts across source tasks. We obtain representative source prompts corresponding to the samples from the posterior utilizing Stein Variational Gradient Descent, which are then aggregated to constitute the initial target prompt. We show extensive experimental results on the standard benchmark NLP tasks, where our Bayesian multi-task transfer learning approach outperforms the state-of-the-art methods in many settings. Furthermore, our approach requires no auxiliary models other than the prompt itself, achieving a high degree of parameter efficiency.
用于软提示调整的贝叶斯多任务转移学习
提示调整是指对提示进行优化,使大规模预训练语言模型适应下游任务,而不是对全部模型参数进行微调,这种方法在多任务迁移学习环境中训练提示时尤为有效。这些方法通常是针对每个源任务单独训练提示语,然后将其汇总,为目标任务的提示语提供初始化。然而,这种方法严重忽视了这样一个事实,即某些源任务之间可能存在消极或积极的干扰。我们认为,当我们通过训练源提示从源任务中提取知识时,我们需要考虑源任务之间的这种相关性,以便更好地转移到目标任务中。为此,我们提出了一种贝叶斯方法,利用源任务中提示的后验分布。我们利用 Stein Variational Gradient Descent 从后验分布中获得与样本相对应的具有代表性的源提示,然后将其汇总构成初始目标提示。我们在标准基准 NLP 任务上展示了大量实验结果,我们的贝叶斯多任务迁移学习方法在许多情况下都优于最先进的方法。此外,除了提示本身,我们的方法不需要任何辅助模型,从而实现了高度的参数效率。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信