从最近的任务投票:下游任务预训练模型的元投票修剪

Haiyan Zhao, Tianyi Zhou, Guodong Long, Jing Jiang, Chengqi Zhang
{"title":"从最近的任务投票:下游任务预训练模型的元投票修剪","authors":"Haiyan Zhao, Tianyi Zhou, Guodong Long, Jing Jiang, Chengqi Zhang","doi":"10.48550/arXiv.2301.11560","DOIUrl":null,"url":null,"abstract":"As a few large-scale pre-trained models become the major choices of various applications, new challenges arise for model pruning, e.g., can we avoid pruning the same model from scratch for every downstream task? How to reuse the pruning results of previous tasks to accelerate the pruning for a new task? To address these challenges, we create a small model for a new task from the pruned models of similar tasks. We show that a few fine-tuning steps on this model suffice to produce a promising pruned-model for the new task. We study this ''meta-pruning'' from nearest tasks on two major classes of pre-trained models, convolutional neural network (CNN) and vision transformer (ViT), under a limited budget of pruning iterations. Our study begins by investigating the overlap of pruned models for similar tasks and how the overlap changes over different layers and blocks. Inspired by these discoveries, we develop a simple but effective ''Meta-Vote Pruning (MVP)'' method that significantly reduces the pruning iterations for a new task by initializing a sub-network from the pruned models of its nearest tasks. In experiments, we demonstrate MVP's advantages in accuracy, efficiency, and generalization through extensive empirical studies and comparisons with popular pruning methods over several datasets.","PeriodicalId":74091,"journal":{"name":"Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Voting from Nearest Tasks: Meta-Vote Pruning of Pre-trained Models for Downstream Tasks\",\"authors\":\"Haiyan Zhao, Tianyi Zhou, Guodong Long, Jing Jiang, Chengqi Zhang\",\"doi\":\"10.48550/arXiv.2301.11560\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"As a few large-scale pre-trained models become the major choices of various applications, new challenges arise for model pruning, e.g., can we avoid pruning the same model from scratch for every downstream task? How to reuse the pruning results of previous tasks to accelerate the pruning for a new task? To address these challenges, we create a small model for a new task from the pruned models of similar tasks. We show that a few fine-tuning steps on this model suffice to produce a promising pruned-model for the new task. We study this ''meta-pruning'' from nearest tasks on two major classes of pre-trained models, convolutional neural network (CNN) and vision transformer (ViT), under a limited budget of pruning iterations. Our study begins by investigating the overlap of pruned models for similar tasks and how the overlap changes over different layers and blocks. Inspired by these discoveries, we develop a simple but effective ''Meta-Vote Pruning (MVP)'' method that significantly reduces the pruning iterations for a new task by initializing a sub-network from the pruned models of its nearest tasks. In experiments, we demonstrate MVP's advantages in accuracy, efficiency, and generalization through extensive empirical studies and comparisons with popular pruning methods over several datasets.\",\"PeriodicalId\":74091,\"journal\":{\"name\":\"Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-01-27\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2301.11560\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2301.11560","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

随着一些大规模预训练模型成为各种应用的主要选择,对模型修剪提出了新的挑战,例如,我们能否避免为每个下游任务从头开始修剪相同的模型?如何重用以前任务的剪枝结果来加速新任务的剪枝?为了应对这些挑战,我们从类似任务的精简模型中为新任务创建一个小模型。我们展示了这个模型上的几个微调步骤足以为新任务产生一个有希望的修剪模型。我们在有限的剪枝迭代预算下,从卷积神经网络(CNN)和视觉变压器(ViT)两大类预训练模型的最近任务上研究了这种“元剪枝”。我们的研究首先调查了类似任务的修剪模型的重叠,以及重叠在不同层和块上的变化。受这些发现的启发,我们开发了一种简单而有效的“元投票修剪(MVP)”方法,该方法通过从最近任务的修剪模型初始化子网络来显着减少新任务的修剪迭代。在实验中,我们通过广泛的实证研究和与几个数据集上流行的修剪方法的比较,证明了MVP在准确性、效率和泛化方面的优势。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Voting from Nearest Tasks: Meta-Vote Pruning of Pre-trained Models for Downstream Tasks
As a few large-scale pre-trained models become the major choices of various applications, new challenges arise for model pruning, e.g., can we avoid pruning the same model from scratch for every downstream task? How to reuse the pruning results of previous tasks to accelerate the pruning for a new task? To address these challenges, we create a small model for a new task from the pruned models of similar tasks. We show that a few fine-tuning steps on this model suffice to produce a promising pruned-model for the new task. We study this ''meta-pruning'' from nearest tasks on two major classes of pre-trained models, convolutional neural network (CNN) and vision transformer (ViT), under a limited budget of pruning iterations. Our study begins by investigating the overlap of pruned models for similar tasks and how the overlap changes over different layers and blocks. Inspired by these discoveries, we develop a simple but effective ''Meta-Vote Pruning (MVP)'' method that significantly reduces the pruning iterations for a new task by initializing a sub-network from the pruned models of its nearest tasks. In experiments, we demonstrate MVP's advantages in accuracy, efficiency, and generalization through extensive empirical studies and comparisons with popular pruning methods over several datasets.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Explaining Full-disk Deep Learning Model for Solar Flare Prediction using Attribution Methods Offline Reinforcement Learning with On-Policy Q-Function Regularization Visualizing Overlapping Biclusterings and Boolean Matrix Factorizations An Examination of Wearable Sensors and Video Data Capture for Human Exercise Classification Online Network Source Optimization with Graph-Kernel MAB
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1