Easy Transfer Learning By Exploiting Intra-domain Structures

04/02/2019
by   Jindong Wang, et al.
18

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 of existing transfer feature learning methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 5

page 6

page 7

research
09/23/2017

Constrained Deep Transfer Feature Learning and its Applications

Feature learning with deep models has achieved impressive results for bo...
research
12/25/2017

Stratified Transfer Learning for Cross-domain Activity Recognition

In activity recognition, it is often expensive and time-consuming to acq...
research
08/18/2017

Learning to Transfer

Transfer learning borrows knowledge from a source domain to facilitate l...
research
04/29/2023

Limits of Model Selection under Transfer Learning

Theoretical studies on transfer learning or domain adaptation have so fa...
research
11/27/2019

Transfer Learning in Visual and Relational Reasoning

Transfer learning is becoming the de facto solution for vision and text ...
research
11/12/2021

Scalable Diverse Model Selection for Accessible Transfer Learning

With the preponderance of pretrained deep learning models available off-...
research
10/15/2018

Hyperparameter Learning via Distributional Transfer

Bayesian optimisation is a popular technique for hyperparameter learning...

Please sign up or login with your details

Forgot password? Click here to reset