迁移学习综述:A Survey on Transfer Learning

本文介绍了迁移学习的四种主流方法:直接迁移源域数据、映射源域和目标域到同一空间、网络架构迁移(fine-tune)及利用GAN进行对抗迁移。探讨了TCA、MMC等概念,并提及了适合迁移的网络结构。

摘要生成于 C知道 ,由 DeepSeek-R1 满血版支持, 前往体验 >

在会议上听一位老师介绍得一篇比较权威的迁移学习综述,
https://arxiv.org/pdf/1808.01974.pdf
文章中总结了目前迁移学习的四种方法:
1,直接对源域数据集进行迁移,给源域数据集加上适当的权重与目标域数据集共同训练样本。
2,将源域和目标域数据集共同映射到同一个数据空间,对新数据空间中的数据进行训练,提到了TCA和MMC两个概念目前还不懂需要深入了解。(
参考文献中关于如何哪些网络结构适合迁移的文献,需要读一读:
Yosinski, J., Clune, J., Bengio, Y., Lipson, H.: How transferable are features in deep neural networks? In: Advances in neural information processing systems. pp.)
3,直接对网络架构进行迁移,就是finetune训练好的模型,因为网络前面层提取的特征往往是通用的。
4,利用GAN的思想进行对抗迁移学习,加鉴别器对不同域的特征进行鉴别,促使网络学习到更加通用的特征。

Abstract—Transfer learning aims at improving the performance of target learners on target domains by transferring the knowledge contained in different but related source domains. In this way, the dependence on a large number of target domain data can be reduced for constructing target learners. Due to the wide application prospects, transfer learning has become a popular and promising area in machine learning. Although there are already some valuable and impressive surveys on transfer learning, these surveys introduce approaches in a relatively isolated way and lack the recent advances in transfer learning. As the rapid expansion of the transfer learning area, it is both necessary and challenging to comprehensively review the relevant studies. This survey attempts to connect and systematize the existing transfer learning researches, as well as to summarize and interpret the mechanisms and the strategies in a comprehensive way, which may help readers have a better understanding of the current research status and ideas. Different from previous surveys, this survey paper reviews over forty representative transfer learning approaches from the perspectives of data and model. The applications of transfer learning are also briefly introduced. In order to show the performance of different transfer learning models, twenty representative transfer learning models are used for experiments. The models are performed on three different datasets, i.e., Amazon Reviews, Reuters-21578, and Office-31. And the experimental results demonstrate the importance of selecting appropriate transfer learning models for different applications in practice.
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值