Deep semi-supervised learning for domain adaptation
Authors:
- 1 September 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15512541,p. 1-6
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.Keywords
This publication has 8 references indexed in Scilit:
- Bayesian Speech and Language Processing2015
- Representation Learning Using Multi-Task Deep Neural Networks for Semantic Classification and Information Retrieval2015
- Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks2014
- Multi-View and Multi-Objective Semi-Supervised Learning for HMM-Based Automatic Speech RecognitionIEEE Transactions on Audio, Speech, and Language Processing, 2012
- Domain Adaptation via Transfer Component AnalysisIEEE Transactions on Neural Networks, 2010
- A Survey on Transfer LearningIEEE Transactions on Knowledge and Data Engineering, 2009
- Domain adaptation with structural correspondence learning2006
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998