DEEP SEMI-SUPERVISED LEARNING FOR DOMAIN ADAPTATION

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 autoencoder, 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.