Marginalized Denoising Autoencoders for Domain Adaptation

Abstract

Stacked denoising autoencoders (SDAs) have been successfully used to learn new representations for domain adaptation. Recently, they have attained record accuracy on standard benchmark tasks of sentiment analysis across different text domains. SDAs learn robust data representations by reconstruction, recovering original features from data that are artificially corrupted with noise. In this paper, we propose marginalized SDA (mSDA) that addresses two crucial limitations of SDAs: high computational cost and lack of scalability to high-dimensional features. In contrast to SDAs, our approach of mSDA marginalizes noise and thus does not require stochastic gradient descent or other optimization algorithms to learn parameters — in fact, they are computed in closed-form. Consequently, mSDA, which can be implemented in only 20 lines of MATLAB, significantly speeds up SDAs by two orders of magnitude. Furthermore, the representations learnt by mSDA are as effective as the traditional SDAs, attaining almost identical accuracies in benchmark tasks.

Extracted Key Phrases

3 Figures and Tables

050100201220132014201520162017
Citations per Year

243 Citations

Semantic Scholar estimates that this publication has 243 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@article{Chen2012MarginalizedDA, title={Marginalized Denoising Autoencoders for Domain Adaptation}, author={Minmin Chen and Zhixiang Eddie Xu and Kilian Q. Weinberger and Fei Sha}, journal={CoRR}, year={2012}, volume={abs/1206.4683} }