Marginalized Denoising Autoencoders for Domain Adaptation

TL;DR

This paper introduces marginalized denoising autoencoders (mSDA), a scalable and computationally efficient variant of stacked denoising autoencoders that achieves comparable accuracy in domain adaptation tasks.

Contribution

The paper presents mSDA, which reduces computational cost and improves scalability of SDAs by marginalizing noise and providing closed-form solutions, enabling faster training.

Findings

mSDA significantly speeds up training compared to SDAs.

mSDA achieves nearly identical accuracy to SDAs on benchmark tasks.

Implementation of mSDA is concise, taking only about 20 lines of MATLAB code.

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^{TM}, 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.