Deep semi-supervised learning for domain adaptation

Hung Yu Chen, Jen-Tzung Chien

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

11 Scopus citations

Abstract

Domain adaptation aims to adapt a classifier from source domain to target domain through learning a good feature representation that allows knowledge to be shared and transferred across domains. Most of previous studies are restricted to extract features and train classifier separately under a shallow model structure. In this paper, we propose a semi-supervised domain adaptation method which co-trains the feature representation and pattern classification under deep neural network (DNN) framework. The labeling in target domain is not required. We treat the hidden layers in DNN as feature extraction and construct the output layer consisting of classification and regression. Our idea is to conduct the feature-based domain adaptation which jointly minimizes the divergence between the distributions from labeled and unlabeled data in both domains, the reconstruction errors due to an auto-encoder, and the classification errors due to the labeled data in source domain. Experiments on image recognition and sentiment classification show the superiority of DNN co-training for domain adaptation.

Original languageEnglish
Title of host publication2015 IEEE International Workshop on Machine Learning for Signal Processing - Proceedings of MLSP 2015
EditorsDeniz Erdogmus, Serdar Kozat, Jan Larsen, Murat Akcakaya
PublisherIEEE Computer Society
ISBN (Electronic)9781467374545
DOIs
StatePublished - 10 Nov 2015
Event25th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2015 - Boston, United States
Duration: 17 Sep 201520 Sep 2015

Publication series

NameIEEE International Workshop on Machine Learning for Signal Processing, MLSP
Volume2015-November
ISSN (Print)2161-0363
ISSN (Electronic)2161-0371

Conference

Conference25th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2015
CountryUnited States
CityBoston
Period17/09/1520/09/15

Keywords

  • Auto-encoder
  • co-training
  • Deep learning
  • domain adaptation
  • semi-supervised learning

Fingerprint Dive into the research topics of 'Deep semi-supervised learning for domain adaptation'. Together they form a unique fingerprint.

Cite this