A Theory of Multiple-Source Adaptation with Limited Target Labeled Data

07/19/2020
by   Yishay Mansour, et al.
0

We study multiple-source domain adaptation, when the learner has access to abundant labeled data from multiple-source domains and limited labeled data from the target domain. We analyze existing algorithms for this problem, and propose a novel algorithm based on model selection. Our algorithms are efficient, and experiments on real data-sets empirically demonstrate their benefits.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/19/2019

Butterfly: Robust One-step Approach towards Wildly-unsupervised Domain Adaptation

Unsupervised domain adaptation (UDA) trains with clean labeled data in s...
research
08/12/2022

Private Domain Adaptation from a Public Source

A key problem in a variety of applications is that of domain adaptation ...
research
11/20/2012

Domain Adaptations for Computer Vision Applications

A basic assumption of statistical learning theory is that train and test...
research
04/25/2022

Algorithms and Theory for Supervised Gradual Domain Adaptation

The phenomenon of data distribution evolving over time has been observed...
research
02/06/2019

Adversarial Domain Adaptation for Stance Detection

This paper studies the problem of stance detection which aims to predict...
research
06/15/2023

Differentially Private Domain Adaptation with Theoretical Guarantees

In many applications, the labeled data at the learner's disposal is subj...

Please sign up or login with your details

Forgot password? Click here to reset