Can I read Easy Transfer Learning By Exploiting Intra-domain Structures on EtoBox?

Easy Transfer Learning By Exploiting Intra-domain Structures by Wang, Jindong; Chen, Yiqiang; Yu, Han; Huang, Meiyu; Yang, Qiang is a scholarly article available to read on EtoBox.

What is Easy Transfer Learning By Exploiting Intra-domain Structures about?

Transfer learning aims at transferring knowledge from a well-labeled domain to a similar but different domain with limited or no labels. Unfortunately, existing learning-based methods often involve intensive model selection and hyperparameter tuning to obtain good results. Moreover, cross-validation is not possible for tuning hyperparameters since there are often no labels in the target domain. This would restrict wide applicability of transfer learning especially in computationally-constraint devices such as wearables. In this paper, we propose a practically Easy Transfer Learning (EasyTL) approach which requires no model selection and hyperparameter tuning, while achieving competitive performance. By exploiting intra-domain structures, EasyTL is able to learn both non-parametric transfer features and classifiers. Extensive experiments demonstrate that, compared to state-of-the-art traditional and deep methods, EasyTL satisfies the Occam's Razor principle: it is extremely easy to implement and use while achieving comparable or better performance in classification accuracy and much better computational efficiency. Additionally, it is shown that EasyTL can increase the performance o

Author

Wang, Jindong; Chen, Yiqiang; Yu, Han; Huang, Meiyu; Yang, Qiang

Published

2019

Language

EN